slavachalnev

TL;DR: I train a model to translate LLM activations into natural language, using cycle consistency as a training signal (activation → description → reconstructed activation). The outputs are often plausible, but they are very lossy and are usually guesses about the context surrounding the activation, not good descriptions of the...

This is a research report about my attempt to extract interpretable features from a transformer MLP by distilling it into a larger student MLP, while encouraging sparsity by applying an L1 penalty to the activations, as depicted in Figure 1. I investigate the features learned by the distilled MLP, compare...