Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwon, Dahee, Lee, Sehyun, Choi, Jaesik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908477088071680
author Kwon, Dahee
Lee, Sehyun
Choi, Jaesik
author_facet Kwon, Dahee
Lee, Sehyun
Choi, Jaesik
contents Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed nature of representations, pinpointing where specific visual concepts are encoded within a model remains a crucial yet challenging task. In this paper, we introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query. To construct each circuit, our method iteratively assesses inter-neuron connectivity, focusing on both functional dependencies and semantic alignment. By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models and is the first to identify circuits tied to specific visual concepts at a fine-grained level. We validate the versatility and effectiveness of GCCs across various deep image classification models.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01728
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
Kwon, Dahee
Lee, Sehyun
Choi, Jaesik
Computer Vision and Pattern Recognition
Artificial Intelligence
Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed nature of representations, pinpointing where specific visual concepts are encoded within a model remains a crucial yet challenging task. In this paper, we introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query. To construct each circuit, our method iteratively assesses inter-neuron connectivity, focusing on both functional dependencies and semantic alignment. By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models and is the first to identify circuits tied to specific visual concepts at a fine-grained level. We validate the versatility and effectiveness of GCCs across various deep image classification models.
title Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.01728