Unverified50% confidenceBenchmarkExact time
In 2024, Anthropic used sparse autoencoders to extract 34 million features from Claude Sonnet and located the internal circuits corresponding to specific concepts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedIn 2024, Anthropic extended mechanistic interpretability methods to Claude 3 Sonnet-level models, identifying millions of interpretable features, including features corresponding to concepts such as deception and sycophancy.79% similarPartially VerifiedIn 2024, Anthropic's mechanistic interpretability team used sparse autoencoders to extract millions of interpretable concept units from the Claude model.73% similarVerifiedClaude 3.5 Sonnet is a model released by Anthropic in 2024 that surpassed the contemporaneous GPT-4o on the code generation benchmark HumanEval71% 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.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046073API
curl https://kongchang.com/api/v1/knowledge/claims/1046073MCP
get_claim(id=1046073)