Lee Sharkey
@leedsharkey
Scruting matrices @ Goodfire | Previously: cofounded Apollo Research
1.6K Following 3.3K Followers
My team at @GoodfireAI has been cooking up a new way to do interpretability: decompose a language model’s weights, not its activations.
Our decomposition natively handles attention (!) and behaves less like a lookup table and more like a generalizing algorithm. (1/6)
Show more
