Unverified50% confidenceReleaseExact time
Anthropic于2023年发表论文《Towards Monosemanticity》，首次在百万参数级别模型中识别出数万个单语义特征
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
VerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.76% 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.74% similarUnverifiedIn a paper published by Anthropic in 2023, sparse autoencoders were used to find tens of thousands of interpretable features in Claude, including emotional states and programming language types.70% similarUnverifiedIn 2024, Anthropic successfully decomposed millions of interpretable features in the Claude model using sparse autoencoders (SAE).69% similarUnverifiedAnthropic is about to release a new reasoning model.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/523916API
curl https://kongchang.com/api/v1/knowledge/claims/523916MCP
get_claim(id=523916)