Note mostly to myself: I posted this also on the Open Source mech interp slack, and got useful comments from Aidan Stewart, Dan Braun, & Lee Sharkey. Summarizing their points:
Aidan: ‘are the SAE features for deception/sycophancy/etc more robust than other methods of probing for deception/sycophancy/etc’, and in general evaluating how SAEs behave under significant distributional shifts seems interesting?
Dan: I’m confident that pure steering based on plain SAE features will not be very safety relevant. This isn’t to say I don’t think it will be useful to explore right now, we need to know the limits of these methods...I think that [steering will not be fully reliable], for one or more of reasons 1-3 in your first msg.
Lee: Plain SAE won’t get all the important features, see recent work on e2e SAE. Also there is probably no such thing as ‘all the features’. I view it more as a continuum that we just put into discrete buckets for our convenience.
Note mostly to myself: I posted this also on the Open Source mech interp slack, and got useful comments from Aidan Stewart, Dan Braun, & Lee Sharkey. Summarizing their points:
Aidan: ‘are the SAE features for deception/sycophancy/etc more robust than other methods of probing for deception/sycophancy/etc’, and in general evaluating how SAEs behave under significant distributional shifts seems interesting?
Dan: I’m confident that pure steering based on plain SAE features will not be very safety relevant. This isn’t to say I don’t think it will be useful to explore right now, we need to know the limits of these methods...I think that [steering will not be fully reliable], for one or more of reasons 1-3 in your first msg.
Lee: Plain SAE won’t get all the important features, see recent work on e2e SAE. Also there is probably no such thing as ‘all the features’. I view it more as a continuum that we just put into discrete buckets for our convenience.
Also Stephen Casper feels that this work underperformed his expectations; see also discussion on that post.