LLM-Driven Feature Discovery
alignmentforum.org 3 months ago 8
Researchers developed a method using large language models to automatically discover interpretable features in neural networks by having the LLM generate explanations and identify patterns without human annotation. The approach processed thousands of features through an LLM to create concise, human-readable descriptions of what network components detect. This enables faster interpretation of what neural networks learn, potentially improving our ability to understand and audit AI model behavior.