# Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video

arXiv: https://arxiv.org/abs/2504.19475 · HTML: https://mlsanity.com/paper/2504.19475/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting vision and multimodal models, one of 13 directions in Mechanistic interpretability.
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Placed in

- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [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)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [Transcoders Find Interpretable LLM Feature Circuits](https://mlsanity.com/paper/2406.11944/) (2024)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [REPAIR: Removing Representation Bias by Dataset Resampling](https://mlsanity.com/paper/1904.07911/) (2019)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [Sparse autoencoders reveal selective remapping of visual concepts during adaptation](https://mlsanity.com/paper/2412.05276/) (2024)
- [Steering CLIP's vision transformer with sparse autoencoders](https://mlsanity.com/paper/2504.08729/) (2025)
- [Interpreting the Second-Order Effects of Neurons in CLIP](https://mlsanity.com/paper/2406.04341/) (2024)
- [Analyzing Vision Transformers for Image Classification in Class Embedding Space](https://mlsanity.com/paper/2310.18969/) (2023)
- [Towards Evaluating Explanations of Vision Transformers for Medical Imaging](https://mlsanity.com/paper/2304.06133/) (2023)
- [Understanding Video Transformers via Universal Concept Discovery](https://mlsanity.com/paper/2401.10831/) (2024)
- [Video Time: Properties, Encoders and Evaluation](https://mlsanity.com/paper/1807.06980/) (2018)
- [Is Appearance Free Action Recognition Possible?](https://mlsanity.com/paper/2207.06261/) (2022)
- [Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks](https://mlsanity.com/paper/2211.01783/) (2022)

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

- [Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?](https://mlsanity.com/paper/2602.14111/) (2026)
- [From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens](https://mlsanity.com/paper/2510.02292/) (2025)
- [Adversarial Attacks Leverage Interference Between Features in Superposition](https://mlsanity.com/paper/2510.11709/) (2025)
- [Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval](https://mlsanity.com/paper/2512.03276/) (2025)
- [From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers](https://mlsanity.com/paper/2509.06938/) (2025)
- [A Geometric Unification of Concept Learning with Concept Cones](https://mlsanity.com/paper/2512.07355/) (2025)
- [DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces](https://mlsanity.com/paper/2505.18441/) (2025)
- [Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts](https://mlsanity.com/paper/2511.06048/) (2025)
- [Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning](https://mlsanity.com/paper/2601.20075/) (2026)
- [Interpreto: An Explainability Library for Transformers](https://mlsanity.com/paper/2512.09730/) (2025)
- [Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers](https://mlsanity.com/paper/2604.14477/) (2026)
- [VFUSE: Virulent Feature Understanding with Sparse autoEncoders](https://mlsanity.com/paper/2606.10080/) (2026)
- [CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models](https://mlsanity.com/paper/2507.19420/) (2025)
- [The Deleuzian Representation Hypothesis](https://mlsanity.com/paper/2512.19734/) (2025)
- [DreamReader: An Interpretability Toolkit for Text-to-Image Models](https://mlsanity.com/paper/2603.13299/) (2026)
- [Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples](https://mlsanity.com/paper/2604.22477/) (2026)
- [When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations](https://mlsanity.com/paper/2606.16196/) (2026)
- [Meta-learning as a principle for human-like visual representations](https://mlsanity.com/paper/2606.28399/) (2026)
- [IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers](https://mlsanity.com/paper/2608.05122/) (2026)
- [Multimodal Model Diffing for Feature Discovery and Control](https://mlsanity.com/paper/2608.09928/) (2026)
- [SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates](https://mlsanity.com/paper/2608.16251/) (2026)

## Abstract (arXiv)

Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hindered by the lack of accessible frameworks and pre-trained weights. We present Prisma (Access the codebase here: https://github.com/Prisma-Multimodal/ViT-Prisma), an open-source framework designed to accelerate vision mechanistic interpretability research, providing a unified toolkit for accessing 75+ vision and video transformers; support for sparse autoencoder (SAE), transcoder, and crosscoder training; a suite of 80+ pre-trained SAE weights; activation caching, circuit analysis tools, and visualization tools; and educational resources. Our analysis reveals surprising findings, including that effective vision SAEs can exhibit substantially lower sparsity patterns than language SAEs, and that in some instances, SAE reconstructions can decrease model loss. Prisma enables new research directions for understanding vision model internals while lowering barriers to entry in this emerging field.