# Decomposing and Editing Predictions by Modeling Model Computation

arXiv: https://arxiv.org/abs/2404.11534 · HTML: https://mlsanity.com/paper/2404.11534/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 92 of its 114 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 30 of 92)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [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)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)

## Built on by (most cited first, 19 of 19)

- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [Interpreting the Second-Order Effects of Neurons in CLIP](https://mlsanity.com/paper/2406.04341/) (2024)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Learned feature representations are biased by complexity, learning order, position, and more](https://mlsanity.com/paper/2405.05847/) (2024)
- [Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP](https://mlsanity.com/paper/2406.01583/) (2024)
- [ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs](https://mlsanity.com/paper/2505.17495/) (2025)
- [Learning to Attribute with Attention](https://mlsanity.com/paper/2504.13752/) (2025)
- [Unveiling Concept Attribution in Diffusion Models](https://mlsanity.com/paper/2412.02542/) (2024)
- [Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models](https://mlsanity.com/paper/2509.17588/) (2025)
- [When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models](https://mlsanity.com/paper/2406.13131/) (2024)
- [Jet Expansions of Residual Computation](https://mlsanity.com/paper/2410.06024/) (2024)
- [Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability](https://mlsanity.com/paper/2501.18887/) (2025)
- [Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers](https://mlsanity.com/paper/2606.06664/) (2026)
- [Position: Capability Control Should be a Separate Goal From Alignment](https://mlsanity.com/paper/2602.05164/) (2026)
- [CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept](https://mlsanity.com/paper/2410.10866/) (2024)
- [Efficiently Verifiable Proofs of Data Attribution](https://mlsanity.com/paper/2508.10866/) (2025)
- [ModHiFi: Identifying High Fidelity predictive components for Model Modification](https://mlsanity.com/paper/2511.19566/) (2025)
- [SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks](https://mlsanity.com/paper/2512.15938/) (2025)
- [Multi-component Causal Tracing in Large Language Models](https://mlsanity.com/paper/2606.03085/) (2026)

## Abstract (arXiv)

How does the internal computation of a machine learning model transform inputs into predictions? In this paper, we introduce a task called component modeling that aims to address this question. The goal of component modeling is to decompose an ML model's prediction in terms of its components -- simple functions (e.g., convolution filters, attention heads) that are the "building blocks" of model computation. We focus on a special case of this task, component attribution, where the goal is to estimate the counterfactual impact of individual components on a given prediction. We then present COAR, a scalable algorithm for estimating component attributions; we demonstrate its effectiveness across models, datasets, and modalities. Finally, we show that component attributions estimated with COAR directly enable model editing across five tasks, namely: fixing model errors, ``forgetting'' specific classes, boosting subpopulation robustness, localizing backdoor attacks, and improving robustness to typographic attacks. We provide code for COAR at https://github.com/MadryLab/modelcomponents .