Language models can explain neurons in language models

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. Language models have become more capable and more broadly deployed, but our understanding of how they work internally is still very limited. For example, it might be diffic

[misshiki]

“GPT-4を使用して、大規模言語モデル内のニューロンの動作に関する説明を自動的に作成し、それらの説明をスコア付け。これらの (不完全な) 説明と GPT-2 のすべてのニューロンのスコアのデータセットをリリース”