{"id":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","title":"Circuit tracing / attribution graphs (methods)","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7d4ba254716fd13d3a1ffb6518788e304eaa7077bd9d7bce201094eb293518b4/","source_url":"https://transformer-circuits.pub/2025/attribution-graphs/methods.html","text_available":false,"authors":[],"outgoing":[],"incoming":[{"source":"arxiv:2505.13763","target":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","evidence":"url","id":"arxiv:2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/95c4e7c49af162594458624b663c82546ad42167854a2235442954821ea69c65/"},{"source":"url:anthropic.com/research/tracing-thoughts-language-model","target":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","evidence":"url","id":"url:anthropic.com/research/tracing-thoughts-language-model","title":"Tracing thoughts of a language model / Circuit tracing (Anthropic)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6817b4eca1b10533ef10b19c81e7c61b3877f963641fea2a81c5a46f68a233cf/"}],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}