Unverified50% confidenceFactExact time
Anthropic 的 Chris Olah 是机械可解释性领域的代表人物之一
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
因果理论破解大模型黑箱：机械可解释性的新范式
Related Claims
UnverifiedThe field of mechanistic interpretability was largely founded by the Anthropic research team (especially Chris Olah) around 2021 through the "Transformer Circuits" series of papers.62% similarPartially VerifiedClaudeBot is Anthropic's crawler54% similarUnverifiedAnthropic has publicly released an interpretability research tool called Jacobian-Lens.52% similarUnverifiedAnthropic and OpenAI published articles on the concept of Harness Engineering in the same week.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/509890API
curl https://kongchang.com/api/v1/knowledge/claims/509890MCP
get_claim(id=509890)