Position-aware Automatic Circuit Discovery

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Haklay, Tal, Orgad, Hadas, Bau, David, Mueller, Aaron, Belinkov, Yonatan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912223338692608
author Haklay, Tal
Orgad, Hadas
Bau, David
Mueller, Aaron
Belinkov, Yonatan
author_facet Haklay, Tal
Orgad, Hadas
Bau, David
Mueller, Aaron
Belinkov, Yonatan
contents A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery methods: they assume circuits are position-invariant, treating model components as equally relevant across input positions. This limits their ability to capture cross-positional interactions or mechanisms that vary across positions. To address this gap, we propose two improvements to incorporate positionality into circuits, even on tasks containing variable-length examples. First, we extend edge attribution patching, a gradient-based method for circuit discovery, to differentiate between token positions. Second, we introduce the concept of a dataset schema, which defines token spans with similar semantics across examples, enabling position-aware circuit discovery in datasets with variable length examples. We additionally develop an automated pipeline for schema generation and application using large language models. Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04577
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Position-aware Automatic Circuit Discovery
Haklay, Tal
Orgad, Hadas
Bau, David
Mueller, Aaron
Belinkov, Yonatan
Machine Learning
Computation and Language
68T50
I.2.7
A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery methods: they assume circuits are position-invariant, treating model components as equally relevant across input positions. This limits their ability to capture cross-positional interactions or mechanisms that vary across positions. To address this gap, we propose two improvements to incorporate positionality into circuits, even on tasks containing variable-length examples. First, we extend edge attribution patching, a gradient-based method for circuit discovery, to differentiate between token positions. Second, we introduce the concept of a dataset schema, which defines token spans with similar semantics across examples, enabling position-aware circuit discovery in datasets with variable length examples. We additionally develop an automated pipeline for schema generation and application using large language models. Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work.
title Position-aware Automatic Circuit Discovery
topic Machine Learning
Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2502.04577