Research

Data-driven Circuit Discovery for Interpretability of Language Models

Single source1 source14 Oct 2026

arXiv:2605.09129v2 Announce Type: replace Abstract: Circuit study aims to explain how language models (LMs) implement a task by localizing and interpreting a circuit: a computational subgraph responsible for a specific model's behavior.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2605.09129

← Back to all developments · Signals are a development reported by more than one source. See the methodology.