自然语言自编码器生成 LLM 激活的无监督解释 Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations.docx

自然语言自编码器生成 LLM 激活的无监督解释 Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations.docx

NaturalLanguageAutoencodersProduceUnsupervisedExplanationsofLLMActivations

https://transformer-circuits.pub/2026/nla/index.html#introduction

TransformerCircuitsThread

NaturalLanguageAutoencodersProduceUnsupervisedExplanationsofLLMActivations

Authors

KitFraser-Taliente*,Subha

文档评论(0)

1亿VIP精品文档

相关文档