11–20 of 135 posts
It will inevitably learn how to think in a way that translates to one (moral) meaning and back but has an ulterior meaning underneath.
Of course, if you use it to make any decision that can still happen eventually.
> We also release an interactive frontend for exploring NLAs on several open models through a collaboration with Neuronpedia. Whatever they did on LLama didn't work, nothing makes sense in their example where they ask the model to lie about 1+1. Either the model is too old, or whatever they used isn't working, but whatever the autoencoder outputs is nothing like their examples with claude. Gemma is similarly bad.
An auto-encoder is trained on [activation] -AV-> [text] -AR-> [activation], where [activation] belongs to one layer in the LLM model M.
Architecture.:
Model being analyzed (M): >|||||>
Auto-Verbalizer (AV) same as M, with tokens for activation: >|||||>
Auto-Reconstructor (AR) truncated up to the layer being analyzed: ||>
The AR is trained on a simple reconstruction loss.
The AV is trained using an RL objective of reconstruction loss with a KL penalty to keep the verbalizations similar to the initial weights (to maintain linguistic fluency).
- Authors acknowledge, and expect, confabulations in verbalizations: factually incorrect or unsubstantiated statements. But, the internal thought we seek is itself, by definition, unsubstantiated. How can we tell if it is not duplicitous?
- They test this on a layer 2/3 deep into the models. I wonder how shallow and deep abstractions affect thought verbalization?
Beautiful idea, an autoencoder must represent everything without hiding if is to recover the original data closely. So it trains a model to verbalize embeddings well. This reveals what we want to know about the model (such as when it thinks it is being tested, or other hidden thoughts).
Pretty neat work either way.
> Note that nothing in this objective constrains the NLA explanation z to be human-readable, or even to bear any semantic relation to the content of [the activation].
The objective could be optimized even if the verbalizer and reconstructor made up their own “language” to represent the activations, that was not human-readable at all.
To point the model in the right direction, they start out by training on guessed internal thinking:
> we ask Opus to imagine the internal processing of a hypothetical language model reading it.
…before switching to training on the real objective.
Furthermore, the verbalizer and reconstructor models are both initialized from LLMs themselves, and given a prompt instructing them on the task, so they are predisposed to write something that looks like an explanation.
But during training, they could still drift away from these explanations toward a made-up language – either one that overtly looks like gibberish, or one that looks like English but encodes the information in a way that’s unrelated to the meaning of the words.
The fascinating thing is that empirically, they don’t, at least to a significant extent. The researchers verify this by correlating the generated explanations with ground truth revealed in other ways. They also try rewording the explanations (which deserves the semantic meaning but would disturb any encoding that’s unrelated to meaning), and find that the reconstructor can still reconstruct activations.
On the other hand, their downstream result is not very impressive:
> An auditor equipped with NLAs successfully uncovered the target model’s hidden motivation between 12% and 15% of the time
That is apparently better than existing techniques, but still a rather low percentage.
Another interesting point: The LLMs used to initialize the verbalizer and reconstructor are stated to have the “same architecture” as the LLM being analyzed (it doesn’t say “same model” so I imagine it’s a smaller version?). The researchers probably think this architectural similarity might give the models some built-in insight about the target model’s thinking that can be unlocked through training. Does it really though? As far as I can see they don’t run any tests using a different architecture, so there’s no way to know.
I thought that wasn't possible for a text generator?
It will inevitably learn how to think in a way that translates to one (moral) meaning and back but has an ulterior meaning underneath.
Ursula K. Le Guin: 'The artist deals with what cannot be said in words. The artist whose medium is fiction does this in words.'
One question jumps out at me: just because a string of text happens to be a good compressed representation (in the autoencoder) of a model's internal activation, does that necessarily mean the text explains that activation in the context of the model? I want to take a look at what they released a bit more closely. Maybe there's a way that they answer this question? Pretty neat work either way.