Though the overwhelming majority of our explanations rating poorly, we imagine we are able to now use ML methods to additional enhance our potential to supply explanations. For instance, we discovered we had been capable of enhance scores by:
Iterating on explanations. We will enhance scores by asking GPT-4 to give you doable counterexamples, then revising explanations in gentle of their activations.Utilizing bigger fashions to provide explanations. The common rating goes up because the explainer mannequin’s capabilities enhance. Nonetheless, even GPT-4 offers worse explanations than people, suggesting room for enchancment.Altering the structure of the defined mannequin. Coaching fashions with completely different activation capabilities improved clarification scores.
We’re open-sourcing our datasets and visualization instruments for GPT-4-written explanations of all 307,200 neurons in GPT-2, in addition to code for clarification and scoring utilizing publicly accessible fashions on the OpenAI API. We hope the analysis neighborhood will develop new methods for producing higher-scoring explanations and higher instruments for exploring GPT-2 utilizing explanations.
We discovered over 1,000 neurons with explanations that scored no less than 0.8, that means that in response to GPT-4 they account for a lot of the neuron’s top-activating habits. Most of those well-explained neurons will not be very fascinating. Nonetheless, we additionally discovered many fascinating neurons that GPT-4 did not perceive. We hope as explanations enhance we could possibly quickly uncover fascinating qualitative understanding of mannequin computations.