Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Mahale, Ajay Pravin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912959921389568
author Mahale, Ajay Pravin
author_facet Mahale, Ajay Pravin
contents Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09988
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
Mahale, Ajay Pravin
Computation and Language
Artificial Intelligence
68T50
I.2.7; I.2.6
Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.
title Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
topic Computation and Language
Artificial Intelligence
68T50
I.2.7; I.2.6
url https://arxiv.org/abs/2603.09988