Intepretability
Views my own
It's very impressive that this technique could be used alongside existing finetuning tools.
> According to our data, this technique stacks additively with both finetuning
To check my understanding, the evidence for this claim in the paper is Figure 13, where your method stacks with finetuning to increase sycophancy. But there are not currently results on decreasing sycophancy (or any other bad capability), where you show your method stacks with finetuning, right?
(AFAICT currently Figure 13 shows some evidence that activation addition to reduce sycophancy outcompetes finetuning, but you're unsure about the statistical significance due to the low percentages involved)
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
I really appreciated this retrospective, this changed my mind about the sparsity penalty, thanks!
Oops, I was wrong in my initial hunch as I assumed centering writing did something extra. I’ve edited my top level comment, thanks for pointing out my oversight!
No this isn’t about center_unembed, it’s about center_writing_weights as explained here: https://github.com/neelnanda-io/TransformerLens/blob/main/further_comments.md#centering-writing-weights-center_writing_weight
This is turned on by default in TL, so okay I think that there must be something else weird about models rather than just a naive bias that causes you to need to do the difference thing
> Can we just add in times the activations for "Love" to another forward pass and reap the sweet benefits of more loving outputs? Not quite. We found that it works better to pair two activation additions.
Do you have evidence for this? It's totally unsurprising to me that you need to do this on HuggingFace models as the residual stream is very likely to have a constant bias term which you will not want to add to. I saw you used TransformerLens for some part of the project and TL removes the mean from all additions to the residual stream which I would have guessed that this would solve the problem here. EDIT: see reply.
I even tested this:
Empirically in TransformerLens the 5*Love and 5*(Love-Hate) additions were basically identical from a blind trial on myself (I found 5*Love more loving 15 times compared to 5*(Love-Hate) more loving 12 times, and I independently rated which generations were more coherent, and both additions were more coherent 13 times. There were several trials where performance on either loving-ness or coherence seemed identical to me).
I think this point was really overstated. I get the impression the rejected papers were basically turned into the arXiv format as fast as possible and so it was easy for the mods to tell this. However, I've seen submissions to cs.LG like this and this that are clearly from the alignment community. These posts are also not stellar by standards of preprint formatting, and were not rejected, apparently
Does the “ground truth” shows the correct label function on 100% of the training and test data? If so, what’s the relevance of the transformer which imperfectly implements the label function?
I think work that compares base language models to their fine-tuned or RLHF-trained successors seems likely to be very valuable, because i) this post highlights some concrete things that change during training in these models and ii) some believe that a lot of the risk from language models come from these further training steps.
If anyone is interested, I think surveying the various fine-tuned and base models here seems the best open-source resource, at least before CarperAI release some RLHF models.
Oh oops, thanks so much. We'll update the paper accordingly. Nit: it's actually
Ex∼D[˙x⋅x]Ex∼D[||x||22]
(it's just minimizing a quadratic)
ETA: the reason we have complicated equations is that we didn't compute Ex∼D[˙x⋅x] during training (this quantity is kinda weird). However, you can compute γ from quantities that are usually tracked in SAE training. Specifically, γ=12(1+E[||xˆ||22]−E[||x−xˆ||22]E[||x||22]) and all terms here are clearly helpful to track in SAE training.