# EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

arXiv: https://arxiv.org/abs/2502.06852 · HTML: https://mlsanity.com/paper/2502.06852/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model](https://mlsanity.com/paper/2305.00586/) (2023)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking](https://mlsanity.com/paper/2402.14811/) (2024)
- [Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms](https://mlsanity.com/paper/2403.17806/) (2024)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://mlsanity.com/paper/2305.08809/) (2023)
- [Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing](https://mlsanity.com/paper/2410.06331/) (2024)
- [Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT](https://mlsanity.com/paper/2402.12201/) (2024)
- [Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model](https://mlsanity.com/paper/2310.12611/) (2023)
- [Transformer Circuit Faithfulness Metrics are not Robust](https://mlsanity.com/paper/2407.08734/) (2024)
- [Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models](https://mlsanity.com/paper/2405.12522/) (2024)
- [Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2401.03646/) (2024)

## Built on by (most cited first, 21 of 21)

- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Understanding the Repeat Curse in Large Language Models from a Feature Perspective](https://mlsanity.com/paper/2504.14218/) (2025)
- [Mechanistic Interpretability as Statistical Estimation: A Variance Analysis](https://mlsanity.com/paper/2510.00845/) (2025)
- [Understanding How Value Neurons Shape the Generation of Specified Values in LLMs](https://mlsanity.com/paper/2505.17712/) (2025)
- [All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs](https://mlsanity.com/paper/2605.12671/) (2026)
- [COMPKE: Complex Question Answering under Knowledge Editing](https://mlsanity.com/paper/2506.00829/) (2025)
- [Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models](https://mlsanity.com/paper/2508.02360/) (2025)
- [Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework](https://mlsanity.com/paper/2510.03282/) (2025)
- [The Compositional Architecture of Regret in Large Language Models](https://mlsanity.com/paper/2506.15617/) (2025)
- [When Attribution Patching Lies: Diagnosis and a Second-Order Correction](https://mlsanity.com/paper/2606.09899/) (2026)
- [Understanding the Dynamics of Demonstration Conflict in In-Context Learning](https://mlsanity.com/paper/2603.04464/) (2026)
- [Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness](https://mlsanity.com/paper/2603.10771/) (2026)
- [Demystifying Variance in Circuit Discovery of LLMs](https://mlsanity.com/paper/2606.16920/) (2026)
- [Query Circuits: Explaining How Language Models Answer User Prompts](https://mlsanity.com/paper/2509.24808/) (2025)
- [Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages](https://mlsanity.com/paper/2601.08146/) (2026)
- [Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States](https://mlsanity.com/paper/2603.29206/) (2026)
- [CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability](https://mlsanity.com/paper/2607.19317/) (2026)
- [Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept](https://mlsanity.com/paper/2607.20995/) (2026)
- [Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit](https://mlsanity.com/paper/2608.27254/) (2026)
- [Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs](https://mlsanity.com/paper/2609.25602/) (2026)
- [Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training](https://mlsanity.com/paper/2609.35890/) (2026)

## Abstract (arXiv)

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit existing gradient-based circuit identification methods and find that their performance is either affected by the zero-gradient problem or saturation effects, where edge attribution scores become insensitive to input changes, resulting in noisy and unreliable attribution evaluations for circuit components. To address the saturation effect, we propose Edge Attribution Patching with GradPath (EAP-GP), EAP-GP introduces an integration path, starting from the input and adaptively following the direction of the difference between the gradients of corrupted and clean inputs to avoid the saturated region. This approach enhances attribution reliability and improves the faithfulness of circuit identification. We evaluate EAP-GP on 6 datasets using GPT-2 Small, GPT-2 Medium, and GPT-2 XL. Experimental results demonstrate that EAP-GP outperforms existing methods in circuit faithfulness, achieving improvements up to 17.7%. Comparisons with manually annotated ground-truth circuits demonstrate that EAP-GP achieves precision and recall comparable to or better than previous approaches, highlighting its effectiveness in identifying accurate circuits.