Goodfire finds neuron communities via gradient attribution, then ablates them to verify causality

burny_tech · x · 2026-11-18

Interpretability company Goodfire describes a method for discovering behavior-linked neuron communities inside models without specifying behaviors in advance.

Pipeline:

The approach enables large-scale, hypothesis-free discovery and causal verification of functional units inside models.

Original post →

More from Research

Research channel →