Everything filed under interpretability

A very early research update describing two experiments I've run using gradient- and weight-based methods to localize behaviors acquired by finetuning within the diff.

Understanding attribution-based and stochastic parameter decomposition methods

Brief notes from the Matryoshka SAEs paper.

Notes on the core sections of Anthropic's Toy Models of Superposition.

Close-reading a classic interpretability paper and trying to make sense of it