Sunday, March 31, 2024

Language fashions can clarify neurons in language fashions

Must read

Though the overwhelming majority of our explanations rating poorly, we consider we will now use ML strategies to additional enhance our skill to provide explanations. For instance, we discovered we have 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 totally different activation capabilities improved rationalization 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 rationalization and scoring utilizing publicly obtainable fashions on the OpenAI API. We hope the analysis group 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 not 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 should not very fascinating. Nonetheless, 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.

Supply hyperlink

More articles


Please enter your comment!
Please enter your name here

Latest article