In Towards Monosemanticity we also did a version of this experiment, and found that the SAE was much less interpretable when the transformer weights were randomized (https://transformer-circuits.pub/2023/monosemantic-features/index.html#appendix-automated-randomized).
Adam Jermyn(Adam Jermyn)
Karma: 1,189
Anthropic’s RSP includes evals after every 4x increase in effective compute and after every 3 months, whichever comes sooner, even if this happens during training, and the policy says that these evaluations include fine-tuning.
This matches my impression. At EAG London I was really stunned (and heartened!) at how many skilled people are pivoting into interpretability from non-alignment fields.
Second, the measure of “features per dimension” used by Elhage et al. (2022) might be misleading. See the paper for details of how they arrived at this quantity. But as shown in the figure above, “features per dimension” is defined as the Frobenius norm of the weight matrix before the layer divided by the number of neurons in the layer. But there is a simple sanity check that this doesn’t pass. In the case of a ReLU network without bias terms, multiplying a weight matrix by a constant factor will cause the “features per dimension” to be increased by that factor squared while leaving the activations in the forward pass unchanged up to linearity until a non-ReLU operation (like a softmax) is performed. And since each component of a softmax’s output is strictly increasing in that component of the input, scaling weight matrices will not affect the classification.
It’s worth noting that Elhage+2022 studied an autoencoder with tied weights and no softmax, so there isn’t actually freedom to rescale the weight matrix without affecting the loss in their model, making the scale of the weights meaningful. I agree that this measure doesn’t generalize to other models/tasks though.
They also define a more fine-grained measure (the dimensionality of each individual feature) in a way that is scale-invariant and which broadly agrees with their coarser measure...
Conditioning Predictive Models: Open problems, Conclusion, and Appendix
Conditioning Predictive Models: Deployment strategy
Conditioning Predictive Models: Interactions with other approaches
Conditioning Predictive Models: Making inner alignment as easy as possible
Conditioning Predictive Models: The case for competitiveness
Conditioning Predictive Models: Outer alignment via careful conditioning
Conditioning Predictive Models: Large language models as predictors
I think there’s tons of low-hanging fruit in toy model interpretability, and I expect at least some lessons from at least some such projects to generalize. A lot of the questions I’m excited about in interpretability are fundamentally accessible in toy models, like “how do models trade off interference and representational capacity?”, “what priors do MLP’s have over different hypotheses about the data distribution?”, etc.
Underspecification of Oracle AI
A thing I really like about the approach in this paper is that it makes use of a lot more of the model’s knowledge of human values than traditional RLHF approaches. Pretrained LLM’s already know a ton of what humans say about human values, and this seems like a much more direct way to point models at that knowledge than binary feedback on samples.
How does this correctness check work?
I usually think of gauge freedom as saying “there is a family of configurations that all produce the same observables”. I don’t think that gives a way to say some configurations are correct/incorrect. Rather some pairs of configurations are equivalent and some aren’t.
That said, I do think you can probably do something like the approach described to assign a label to each equivalence class of configurations and do your evolution in that label space, which avoids having to pick a gauge.
How would you classify optimization shaped like “write a program to solve the problem for you”. It’s not directly searching over solutions (though the program you write might). Maybe it’s a form of amortized optimization?
Separately: The optimization-type distinction clarifies a circle I’ve run around talking about inner optimization with many people, namely “Is optimization the same as search, or is search just one way to get optimization?” And I think this distinction gives me something to point to in saying “search is one way to get (direct) optimization, but there are other kinds of optimization”.
I might be totally wrong here, but could this approach be used to train models that are more likely to be myopic (than e.g. existing RL reward functions)? I’m thinking specifically of the form of myopia that says “only care about the current epoch”, which you could train for by (1) indexing epochs, (2) giving the model access to its epoch index, (3) having the reward function go negative past a certain epoch, (4) giving the model the ability to shutdown. Then you could maybe make a model that only wants to run for a few epochs and then shuts off, and maybe that helps avoid cross-epoch optimization?
That’s definitely a thing that can happen.
I think the surgeon can always be made ~arbitrarily powerful, and the trick is making it not too powerful/trivially powerful (in ways that e.g. preclude the model from performing well despite the surgeon’s interference).
So I think the core question is: are there ways to make a sufficiently powerful surgeon which is also still defeasible by a model that does what we want?
A trick I sometimes use, related to this post, is to ask whether my future self would like to buy back my present time at some rate. This somehow makes your point about intertemporal substitution more visceral for me, and makes it easier to say “oh yes this thing which is pricier than my current rate definitely makes sense at my plausible future rate”.
I’m guessing that the sales numbers aren’t high enough to make $200k if sold at plausible markups?