From the source
OpenAI uses GPT-4 to automatically write and score explanations for neurons in GPT-2, and releases a dataset of these explanations and scores for every neuron in GPT-2.
From the source
From the source
OpenAI uses GPT-4 to automatically write and score explanations for neurons in GPT-2, and releases a dataset of these explanations and scores for every neuron in GPT-2.
From the source
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.
openai.com