· 23 days ago· AI Alignment Forum
Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
Abstract We introduce Natural Language Autoencoders (NLAs), an unsupervised method for generating natural language explanations of LLM activations. An NLA consists of two LLM modules: an activation verbalizer (AV) that maps an activation to a text description and an activation reconstructor (AR) tha
#ai