Language models can explain neurons in language models
核心要点速览
We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset of these (imperfect) explanations and scores for every neuron in GPT-2.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。