All of Lee Sharkey's Comments + Replies

Great! I'm curious, what was it about the sparsity penalty that you changed your mind about? 

2Arthur Conmy2mo
I previously thought that L1 penalties were just exactly what you wanted to do sparse reconstruction.  Thinking about your undershooting claim, I came up with a toy example that made it obvious to me that the Anthropic loss function was not optimal: suppose you are role-playing a single-feature SAE reconstructing the number 2, and are given loss equal to the squared error of your guess, plus the norm of your guess. Then guessing x>0 gives loss minimized at x=3/2, not 2

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.
... (read more)
2Arthur Conmy3mo
I really appreciated this retrospective, this changed my mind about the sparsity penalty, thanks!

Here is a reference that supports the claim using simulations

But I think you're right to flag it - other references don't really support it as the main reason for stripes.

Thanks Akash! 

I agree that this feels neglected.

Markus Anderljung recently tweeted about some upcoming related work from Jide Alaga and Jonas Schuett:

Looking forward to it coming out! 

Bilinear layers - not confident at all! It might make structure more amenable to mathematical analysis so it might help? But as yet there aren't any empirical interpretability wins that have come from bilinear layers.

Dictionary learning - This is one of my main bets for comprehensive interpretability. 

Other areas - I'm also generally excited by the line of research outlined in 

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. 

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 ha... (read more)

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 ot... (read more)

Thanks for your interest!

The autoencoder losses reported are the train losses. And you're right to point at noise potentially being an issue. It's my strong suspicion that some of the problems in these results are due to there being an insufficient number of data points to train the autoencoders on LM data. 

> I would also be interested to test a bit more if this method works on toy models which clearly don't have many features, such as a mixture of a dozen of gaussians, or random points in the unit square (where there is a lot of room "in the corne... (read more)

My usual starting point is “maybe people will make a model-based RL AGI / brain-like AGI”. Then this post is sorta saying “maybe that AGI will become better at planning by reading about murphyjitsu and operations management etc.”, or “maybe that AGI will become better at learning by reading Cal Newport and installing Anki etc.”. Both of those things are true, but to me, they don’t seem safety-relevant at all.

Hm, I don't think this quite captures what I view the post as saying. 

Maybe what you’re thinking is: “Maybe Future Company X will program a

... (read more)
2Steve Byrnes1y
Thanks! See Section 3 here for why I think it would be a lot worse.

That's correct. 'Correlated features' could ambiguously mean "Feature x tends to activate when feature y activates" OR "When we generate feature direction x, its distribution is correlated with feature y's". I don't know if both happen in LMs. The former almost certainly does. The second doesn't really make sense in the context of LMs since features are learned, not sampled from a distribution.

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 indee... (read more)

In the toy datasets, the features have the same scale (uniform from zero to one when active multiplied by a unit vector). However in the NN case, there's no particular reason to think the feature scales are normalized very much (though maybe they're normalized a bit due to weight decay and similar). Is there some reason this is ok? 

Hm it's a great point. There's no principled reason for it. Equivalently, there's no principled reasons to expect the coefficients/activations for each feature to be on the same scale either. We should probably look into a ... (read more)

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.