{"id":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","title":"Attribution graphs, the biology of the model","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8b3e14c537e89eed9a4402e9c14094d69913ed24d45fdab1a82ba4b8280660e2/","source_url":"https://transformer-circuits.pub/2025/attribution-graphs/biology.html","text_available":false,"authors":[],"outgoing":[],"incoming":[{"source":"arxiv:2505.13763","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.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":"arxiv:2508.02513","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","evidence":"url","id":"arxiv:2508.02513","title":"Modular Arithmetic: Language Models Solve Math Digit by Digit","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/83aede757707b76dc76fc15431a436e5dec05563a9f2f28ebcc650775c878bcc/"},{"source":"arxiv:2604.17121","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","evidence":"url","id":"arxiv:2604.17121","title":"The Topological Trouble With Transformers","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7f9d762bbe192e1208f6d7dc289b7e79c23d4bdde0b1b3999ff5fda55b0dcd1a/"},{"source":"url:ai-2027.com","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","evidence":"url","id":"url:ai-2027.com","title":"AI 2027 (Kokotajlo)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3fd447e0ff58689ae00a4666e28bbd7faecd472dec7195ab1d524cb5402a1766/"},{"source":"url:anthropic.com/research/tracing-thoughts-language-model","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.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}