Language fashions can clarify neurons in language fashions

Though the overwhelming majority of our explanations rating poorly, we imagine we will now use ML strategies to additional enhance our potential to supply explanations. For instance, we discovered we have been capable of enhance scores by:

  • Iterating on explanations. We are able to enhance scores by asking GPT-4 to provide you with potential counterexamples, then revising explanations in mild of their activations.
  • Utilizing bigger fashions to provide explanations. The typical rating goes up because the explainer mannequin’s capabilities enhance. Nevertheless, even GPT-4 offers worse explanations than people, suggesting room for enchancment.
  • Altering the structure of the defined mannequin. Coaching fashions with totally different activation features 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 using publicly available models on the OpenAI API. We hope the analysis neighborhood will develop new strategies for producing higher-scoring explanations and higher instruments for exploring GPT-2 utilizing explanations.

We discovered over 1,000 neurons with explanations that scored at the very least 0.8, that means that in line with GPT-4 they account for a lot of the neuron’s top-activating conduct. Most of those well-explained neurons should not very fascinating. Nevertheless, we additionally discovered many fascinating neurons that GPT-4 did not perceive. We hope as explanations enhance we might be able to quickly uncover fascinating qualitative understanding of mannequin computations.

Introducing the ChatGPT app for iOS

New methods to handle your information in ChatGPT