Материал түпнұсқа тілінде: 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.
2023 ж. 9 мамыр · Дереккөз: OpenAI news
Толық мәтін дереккөзде қолжетімді.