AI ALIGNMENT FORUM
AF

All of Philippe Chlenski's Comments + Replies

Transcoders enable fine-grained interpretable circuit analysis for language models
Philippe Chlenski20

Possibly. But there is no optimization pressure from pre-training on the relationship between MLPs and transcoders. The MLPs are the thing that pre-training optimizes (as the "full-precision" master model), while transcoders only need to be maintained to remain in sync with the MLPs

I see. I was in fact misunderstanding this detail in your training setup. In this case, only engineering considerations really remain: these boil down to incorporating multiple transcoders simultaneously and modeling shifting MLP behavior with transcoders. These seem like tracta... (read more)

Reply
Transcoders enable fine-grained interpretable circuit analysis for language models
Philippe Chlenski10

This sounds like it could work. I can think of a few reasons why this approach could be challenging, however:
1. We don't really know how transcoders (or SAEs, to the best of my knowledge) behave when they're being trained to imitate a model component that's still updating
2. Substituting multiple transcoders at once is possible, but degrades model performance a lot compared to single-transcoder substitutions. Substituting one transcoder at a time would require restarting the forward pass at each layer. 
3. If the transcoders are used to predict next tok... (read more)

Reply
2Vladimir Nesov
Possibly. But there is no optimization pressure from pre-training on the relationship between MLPs and transcoders. The MLPs are the thing that pre-training optimizes (as the "full-precision" master model), while transcoders only need to be maintained to remain in sync with the MLPs, whatever they are (according to the same local objective as before, which doesn't care at all about token prediction). The search is for MLPs such that their transcoders are good predictors, not directly for transcoders that are good predictors. Unclear given the extreme quantization results, where similarly post-training replacement would degrade model performance a lot, yet quantization-aware pre-training somehow doesn't. This seems to be the main technical hurdle to do the experiment, updating transcoders both efficiently and correctly, as underlying MLPs gradually change. (I'm guessing some discontinuous jumps in choice of transcoders might be OK.)