Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Article Status
Published
Title
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Date
2024-05-24 13:28:48
Accessed
24/05/2024, 13:28
Extra
Citation Key: 2024k <标题>: 扩展单义性:从 Claude 3 十四行诗中提取可解释特征
Citation
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. (2024, May 24). https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html
Powered by Zotero and Kerko.