Tracr: Compiled Transformers As a Laboratory for Interpretability

NeurIPS 2023（2023）

引用 74|浏览72

关键词

interpretability,transformers,language models,RASP,Tracr,mechanistic interpretability

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要