§ feed · storyline
Language models can explain neurons in language models
OpenAI uses GPT-4 to generate and score explanations for every neuron in GPT-2, releasing the full dataset of explanations and scores publicly.
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.
§ sources1 publication · timeline below