Research engineer at Apollo Research (London).
My main research interests are mechanistic interpretability and inner alignment.
Lee Sharkey(Lee Sharkey)
[Interim research report] Taking features out of superposition with sparse autoencoders
Circumventing interpretability: How to defeat mind-readers
Current themes in mechanistic interpretability research
Sparsify: A mechanistic interpretability research agenda
‘Fundamental’ vs ‘applied’ mechanistic interpretability research
A small update to the Sparse Coding interim research report
A technical note on bilinear layers for interpretability
Theories of Change for AI Auditing
Why almost every RL agent does learned optimization
This is a good idea and is something we’re (Apollo + MATS stream) working on atm. We’re planning on releasing our agenda related to this and, of course, results whenever they’re ready to share.
Thanks for this feedback! I agree that the task & demo you suggested should be of interest to those working on the agenda.
It makes me a bit worried that this post seems to implicitly assume that SAEs work well at their stated purpose.
There were a few purposes proposed, and at multiple levels of abstraction, e.g.
The purpose of being the main building block of a mathematical description used in an ambitious mech interp solution
The purpose of being the main building block of decompiled networks
The purpose of taking features out of superposition
I’m going to assume you meant the first one (and maybe the second). Lmk if not.
Fwiw I’m not totally convinced that SAEs are the ultimate solution for the purposes in the first two bullet points. But I do think they’re currently SOTA for ambitious mech interp purposes, and there is usually scientific benefit of using imperfect but SOTA methods to push the frontier of what we know about network internals. Indeed, I view this as beneficial in the same way that historical applications of (e.g.) causal scrubbing for circuit discovery were beneficial, despite the imperfections of both methods.
I’ll also add a persnickety note that I do explicitly say in the agenda that we should be looking for better methods than SAEs: “It would be nice to have a formal justification for why we should expect sparsification to yield short semantic descriptions. Currently, the justification is simply that it appears to work and a vague assumption about the data distribution containing sparse features. I would support work that critically examines this assumption (though I don’t currently intend to work on it directly), since it may yield a better criterion to optimize than simply ‘sparsity’ or may yield even better interpretability methods than SAEs.”
However, to concede to your overall point, the rest of the article does kinda suggest that we can make progress in interp with SAEs. But as argued above, I’m comfortable that some people in the field proceed with inquiries that use probably imperfect methods.Precisely, I would bet against “mild tweaks on SAEs will allow for interpretability researchers to produce succinct and human understandable explanations that allow for recovering >75% of the training compute of model components”.
I’m curious if you believe that, even if SAEs aren’t the right solution, there realistically exists a potential solution that would allow researchers to produce succinct, human understandable explanation that allow for recovering >75% of the training compute of model components?
I’m wondering if the issue you’re pointing at is the goal rather than the method.
I strongly suspect this is the case too!
In fact, we might be able to speed up the learning of common features even further:
Pierre Peigné at SERIMATS has done some interesting work that looks at initialization schemes that speed up learning. If you initialize the autoencoders with a sample of datapoints (e.g. initialize the weights with a sample from the MLP activations dataset), each of which we assume to contain a linear combination of only a few of the ground truth features, then the initial phases of feature recovery is much faster*. We haven’t had time to check, but it’s presumably biased to recover the most common features first since they’re the most likely to be in a given data point.
*The ground truth feature recovery metric (MMCS) starts higher at the beginning of autoencoder training, but converges to full recovery at about the same time.
This sounds really reasonable. I had only been thinking of a naive version of interpretability tools in the loss function that doesn’t attempt to interpret the gradient descent process. I’d be genuinely enthusiastic about the strong version you outlined. I expect to think a lot about it in the near future.
So, for models that are 10 terabytes in size, you should perhaps be expecting a “model manual” which is around 10 terabytes in size.
Yep, that seems reasonable.
I’m guessing you’re not satisfied with the retort that we should expect AIs to do the heavy lifting here?
Or perhaps you don’t think you need something which is close in accuracy to a full explanation of the network’s behavior.
I think the accuracy you need will depend on your use case. I don’t think of it as a globally applicable quantity for all of interp.
For instance, maybe to ‘audit for deception’ you really only need identify and detect when the deception circuits are active, which will involve explaining only 0.0001% of the network.
But maybe to make robust-to-training interpretability methods you need to understand 99.99...99%.
It seem likely to me that we can unlock more and more interpretability use cases by understanding more and more of the network.
No theoretical reason—The method we used in the Interim Report to combine the two losses into one metric was pretty cursed. It’s probably just better to use L1 loss alone and reconstruction loss alone and then combine the findings. But having plots for both losses would have added more plots without much gain for the presentation. It also just seemed like the method that was hardest to discern the difference between full recovery and partial recovery because the differences were kind of subtle. In future work, some way to use the losses to measure feature recover will probably be re-introduced. It probably just won’t be the way we used in the interim report.
Thanks Erik :) And I’m glad you raised this.
One of the things that many researchers I’ve talked to don’t appreciate is that, if we accept networks can do computation in superposition, then we also have to accept that we can’t just understand the network alone. We want to understand the network’s behaviour on a dataset, where the dataset contains potentially lots of features. And depending on the features that are active in a given datum, the network can do different computations in superposition (unlike in a linear network that can’t do superposition). The combined object ‘(network, dataset)’ is much larger than the network itself.
ExplanationsDescriptions of the (network, dataset) object can actually be compressions despite potentially being larger than the network.So,
One might say that SAEs lead to something like a shorter “description length of what happens on any individual input” (in the sense that fewer features are active). But I don’t think there’s a formalization of this claim that captures what we want. In the limit of very many SAE features, we can just have one feature active at a time, but clearly that’s not helpful.
You can have one feature active for each datapoint, but now we’ve got an
explanationdescription of the (network, dataset) that scales linearly in the size of the dataset, which sucks! Instead, if we look for regularities (opportunities for compression) in how the network treats data, then we have a better chance atexplanationsdescriptions that scale better with dataset size. Suppose a datum consists of a novel combination of previouslyexplaineddescribed circuits. Then ourexplanationdescription of the (network, dataset) is much smaller than if weexplaineddescribed every datapoint anew.In light of that, you can understand my disagreement with “in that case, I could also reduce the description length by training a smaller model.” No! Assuming the network is smaller yet as performant (therefore presumably doing more computation in superposition), then the
explanationdescription of the (network, dataset) is basically unchanged.
And these are both real obstacles. But there are deeper obstacles, that seem to me more central, and that I haven’t observed others to notice on their own.
I just want to point out that I’ve written a long list of such obstacles in this article: Circumventing interpretability: How to defeat mind-readers
I believe the example of deep deception that Nate describes in this post is actually a combination of several methods described in that post.
I’ll quote the parts of this post that correspond to particular interpretability circumvention methods in the other post.
But the highly-generic reaction “spin up a subthread to tackle this newly-discovered obstacle”, or “be concerned about patterns in how long things take”, is something that cannot be readily trained away, and so that much happens without issue.
^ This is an example of what I called ‘representational kludging’. It’s an ugly way to represent “Be concerned about the monitors detecting suspicious instructions”, but it turns out to function similarly to such a representation.
It also involves ‘passively externalised representations’, since the observation that there is a delay in the instruction is a representational proxy for the (banned) observation that the monitors detected something suspicious about the instructions.
A different cognitive subthread: Is it possible to look over the detailed history of instructions and their corresponding delay times, and figure out exactly which sorts of instructions cause delays, and rephrase the instructions to avoid those?
^ This is an example of the AI edging toward ‘thinking in the gaps in our tools’.
Simplify-and-critique didn’t do the trick, but perhaps a nearby strategy can help. One nearby strategy that has recently been proving itself is called simplify/translate/solve, and it involves translating the problem into a common abstract format, and then solving the problem there. (Metaphorically: if you’re having trouble telling whether your basket of apples will divide evenly between three friends, consider translating the question into a numerical representation and using long division.)
Simplify/translate/solve is close in the relevant embedding space to simplify-and-critique, which makes it a natural candidate to consider. (Perhaps some of the simplifications from simplify-and-critique can even be reused.)
Normally, simplify/translate/solve wouldn’t be deployed unless the AI had more familiarity with the original domain, and more of an idea about what translated domain might render the solution easier. But normally, threads don’t hiccup like this. And the overall system has recently been granted more computing power, and avoiding a 200-year wetlab lockup is quite important, so it’s OK to try approaches that might involve more brute force than usual.
^ This is an additional example of ‘representational kludging’, since the AI is using representational tools that are nearby in embedding space but that aren’t exactly appropriate for the job, but have a sufficiently similar function that they still do the job.
Overall comments:
I really liked this post!
I like it because priorly there didn’t exist a compelling story for the broad class of concepts to which it points. And I liked it for the name it gives to that broad class (‘deep deception’). I agree that it’s underappreciated that we’re still in trouble in the world where we (somehow) get good enough interpretability to monitor for and halt deceptive thoughts.
There should be a neat theoretical reason for the clean power law where L1 loss becomes too big. But it doesn’t make intuitive sense to me—it seems like if you just add some useless entries in the dictionary, the effect of losing one of the dimensions you do use on reconstruction loss won’t change, so why should the point where L1 loss becomes too big change? So unless you have a bug (or some weird design choice that divides loss by number of dimensions), those extra dimensions would have to be changing something.
The L1 loss on the activations does indeed take the mean activation value. I think it’s probably a more practical choice than simply taking the sum because it creates independence between hyperparameters: We wouldn’t want the size of the sparsity loss to change wildly relative to the reconstruction loss when we change the dictionary size. In the methods section I forgot to include the averaging terms. I’ve updated the text in the article. Good spot, thanks!
I’d definitely be interested in you including this as a variable in the toy data, and seeing how it affects the hyperparameter search heuristics.
Yeah I think this is probably worth checking too. We probably wouldn’t need to have too many different values to get a rough sense of its effect.
Fig. 9 is cursed. Is there a problem with estimating from just one component of the loss?
Yeah it kind of is… It’s probably better to just look at each loss component separately. Very helpful feedback, thanks!
I’m pretty sure that there’s at least one other MATS group (unrelated to us) currently working on this, although I’m not certain about any of the details. Hopefully they release their research soon!
There’s recent work published on this here by Chris Mathwin, Dennis Akar, and me. The gated attention block is a kind of transcoder adapted for attention blocks.
Nice work by the way! I think this is a promising direction.
Note also the similar, but substantially different, use of the term transcoder here, whose problems were pointed out to me by Lucius. Addressing those problems helped to motivate our interest in the kind of transcoders that you’ve trained in your work!
Comments on the outcomes of the post:
I’m reasonably happy with how this post turned out. I think it probably bought the Anthropic/superposition mechanistic interpretability agenda somewhere between 0.1 to 4 counterfactual months of progress, which feels like a win.
I think sparse autoencoders are likely to be a pretty central method in mechanistic interpretability work for the foreseeable future (which tbf is not very foreseeable).
Two parallel works used the method identified in the post (sparse autoencoders—SAEs) or slight modification:
Cunningham et al. (2023)(https://arxiv.org/abs/2309.08600), a project which I supervised.
Bricken et al. (2023)(https://transformer-circuits.pub/2023/monosemantic-features), the Anthropic paper ‘Towards Monosemanticity’.
That two teams were able to use the results to explore complementary directions in parallel I think partly validates Conjecture’s policy (at that time) of publishing quick, scrappy results that optimize for impact rather than rigour. I make this note because that policy attracted some criticism that I perceived to be undue, and to highlight that some of the benefits of the policy can only be observed after longer periods.
Some regrets related to the post:
It was pretty silly of me to divide the L1 loss by the number of dictionary elements. The idea was that this means that the L1 loss per dictionary element remains roughly constant even as you scale dictionaries. But that isn’t what you want—you want more penalty as you scale, assuming the number of data-generating features is fixed. This made it more difficult than it needed to be to find the right hyperparameters. Fortunately, Logan Smith (iirc) identified this issue while working on Cunningham et al.
The language model results were underwhelming. I strongly suspect they were undertrained. This was a addressed in a follow up post (https://www.alignmentforum.org/posts/DezghAd4bdxivEknM/a-small-update-to-the-sparse-coding-interim-research-report).
I regret giving a specific number of potential features: “Here we found very weak, tentative evidence that, for a model of size d_model = 256, the number of features in superposition was over 100,000. This is a large scaling factor and it’s only a lower bound. If the estimated scaling factor is approximately correct (and, we emphasize, we’re not at all confident in that result yet) or if it gets larger, then this method of feature extraction is going to be very costly to scale to the largest models – possibly more costly than training the models themselves. ” Despite all the qualifications and expressions of deep uncertainty, I got the impression that many people read too much into this. I think avoiding publishing the LM results or not giving a specific figure could have avoided this misunderstanding.
Outlying issues:
In their current formulation, SAEs leave a few important problems unaddressed, including:
SAEs probably don’t learn the most functionally relevant features. They find directions in the activations that are separable, but that doesn’t necessarily reflect the network’s ontology. The features learned by SAEs are probably too granular.
SAEs don’t automatically provide a way to summarize the interactions between features (i.e. there is a gap between features and circuits).
The SAEs used in the above mentioned papers aren’t a very satisfying solution to dealing with attention head polysemanticity.
SAEs optimize two losses: Reconstruction and L1. The L1 loss penalizes the feature coefficients. I think this penalty means that, in expectation, they’ll systematically undershoot the correct prediction for the coefficients (this has been observed empirically in private correspondence).
I and collaborators are working on each of these problems.