Unverified50% confidenceFactExact time
Anthropic在2023年发表的研究表明，通过SAE可以从Claude模型中提取出对应'金门大桥'、'代码错误'等具体概念的单元特征
1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
Related Claims
UnverifiedIn 2024, Anthropic successfully decomposed millions of interpretable features in the Claude model using sparse autoencoders (SAE).78% similarUnverifiedAnthropic published "Towards Monosemanticity" in 2023 and "Scaling and evaluating sparse autoencoders" in 2024, with researchers using SAEs to identify millions of interpretable features in models such as Claude.66% similarUnverifiedAnthropic在2024年发布的研究报告显示，Claude在提供适当工具链后能独立完成端到端的基础渗透测试任务63% similarVerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.62% similarUnverifiedAnthropic曾于2023年公开Claude在claude.ai上使用的完整系统提示，供用户和研究者审计61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/742334API
curl https://kongchang.com/api/v1/knowledge/claims/742334MCP
get_claim(id=742334)