# pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

arXiv: https://arxiv.org/abs/2403.07809 · HTML: https://mlsanity.com/paper/2403.07809/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [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)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack](https://mlsanity.com/paper/1811.09310/) (2018)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Circuit Breaking: Removing Model Behaviors with Targeted Ablation](https://mlsanity.com/paper/2309.05973/) (2023)
- [Uncovering Intermediate Variables in Transformers using Circuit Probing](https://mlsanity.com/paper/2311.04354/) (2023)

## Built on by (most cited first, 30 of 54)

- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions](https://mlsanity.com/paper/2405.13954/) (2024)
- [MIB: A Mechanistic Interpretability Benchmark](https://mlsanity.com/paper/2504.13151/) (2025)
- [NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals](https://mlsanity.com/paper/2407.14561/) (2024)
- [Monitoring Latent World States in Language Models with Propositional Probes](https://mlsanity.com/paper/2406.19501/) (2024)
- [The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?](https://mlsanity.com/paper/2507.08802/) (2025)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models](https://mlsanity.com/paper/2502.17516/) (2025)
- [The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis](https://mlsanity.com/paper/2408.01416/) (2024)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models](https://mlsanity.com/paper/2502.10835/) (2025)
- [HyperSteer: Activation Steering at Scale with Hypernetworks](https://mlsanity.com/paper/2506.03292/) (2025)
- [Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2406.16033/) (2024)
- [Locking Down the Finetuned LLMs Safety](https://mlsanity.com/paper/2410.10343/) (2024)
- [Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions](https://mlsanity.com/paper/2505.16002/) (2025)
- [Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness](https://mlsanity.com/paper/2404.00216/) (2024)
- [Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects](https://mlsanity.com/paper/2406.15955/) (2024)
- [Enhancing Hallucination Detection through Noise Injection](https://mlsanity.com/paper/2502.03799/) (2025)
- [Characterizing the Role of Similarity in the Property Inferences of Language Models](https://mlsanity.com/paper/2410.22590/) (2024)
- [Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention](https://mlsanity.com/paper/2605.29548/) (2026)
- [Mechanistic evaluation of Transformers and state space models](https://mlsanity.com/paper/2505.15105/) (2025)
- [The Geometry of Harmfulness in LLMs through Subconcept Probing](https://mlsanity.com/paper/2507.21141/) (2025)
- [Addressing divergent representations from causal interventions on neural networks](https://mlsanity.com/paper/2511.04638/) (2025)
- [Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models](https://mlsanity.com/paper/2506.18141/) (2025)
- [Modular Arithmetic: Language Models Solve Math Digit by Digit](https://mlsanity.com/paper/2508.02513/) (2025)
- [Penzai + Treescope: A Toolkit for Interpreting, Visualizing, and Editing Models As Data](https://mlsanity.com/paper/2408.00211/) (2024)
- [On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions](https://mlsanity.com/paper/2504.06303/) (2025)
- [Combining Causal Models for More Accurate Abstractions of Neural Networks](https://mlsanity.com/paper/2503.11429/) (2025)
- [Structured Pruning for Diverse Best-of-N Reasoning Optimization](https://mlsanity.com/paper/2506.03978/) (2025)

## Abstract (arXiv)

Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. pyvene supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/stanfordnlp/pyvene.