Материал на языке оригинала: English.
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.
9 мая 2023 г. · Источник: OpenAI news
Полный текст доступен у источника.