I see a lot of takes on Anthropic's sparse autoencoder research like "this is just steering vectors with extra steps" and I strongly feel that this underrates the epistemic utility of doing…
Posters: jd_pressman. jd_pressman
12 likes recorded by the source corpus.
Topics: AI & LLMs
View Post: https://x.com/jd_pressman/status/1794654574495899751