{"id":"url:alignmentforum.org/posts/nffst5mio7bcaqhpa/an-extremely-opinionated-annotated-list-of-my-favourite-1","title":"An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 (Alignment Forum)","date":"2024-07-07","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/28f1f482044fd8bff4e1190eded455473b6882f5493ef64f40f8ab78ec9ba79b/","source_url":"https://www.alignmentforum.org/posts/NfFST5Mio7BCAQHPA/an-extremely-opinionated-annotated-list-of-my-favourite-1","text_available":false,"authors":["Neel Nanda"],"outgoing":[{"source":"url:alignmentforum.org/posts/nffst5mio7bcaqhpa/an-extremely-opinionated-annotated-list-of-my-favourite-1","target":"arxiv:2301.05217","evidence":"id","id":"arxiv:2301.05217","title":"Progress measures for grokking via mechanistic interpretability","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f71e3b65a8b3f35beb171d17f6c65878e0914227a0042ccba59b88952554baef/"}],"incoming":[],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}