Language models can explain neurons in language models
OpenAI Blog
May 9, 2023
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.
Verticals
airesearch
Originally published on OpenAI Blog on 5/9/2023