ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
☆383Jul 23, 2025Updated last year
Alternatives and similar repositories for ViT-Prisma
Users that are interested in ViT-Prisma are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Training Sparse Autoencoders on Language Models☆1,501Updated this week
- Mechanistic Interpretability Visualizations using React☆362Apr 30, 2026Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆269Feb 27, 2026Updated 5 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,790Updated this week
- ☆429Aug 21, 2025Updated 11 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,023Updated this week
- 👋 Overcomplete is a Vision-based SAE Toolbox☆148Dec 4, 2025Updated 8 months ago
- ☆294Oct 1, 2024Updated last year
- Mechanistic understanding and validation of large AI models with SemanticLens☆54Dec 4, 2025Updated 8 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆20May 29, 2024Updated 2 years ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆14Jan 26, 2025Updated last year
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆199Sep 26, 2025Updated 10 months ago
- Sparse autoencoders for vision☆66Updated this week
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Jul 6, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆212Nov 17, 2024Updated last year
- ☆182May 1, 2026Updated 3 months ago
- ☆224Oct 14, 2025Updated 10 months ago
- PyPI package for DualXDA for efficient data attribution and feature-level explanations of training data influence☆22Mar 6, 2026Updated 5 months ago
- Sparsify transformers with SAEs and transcoders☆734Updated this week
- Unified access to Large Language Model modules using NNsight☆119Jul 28, 2026Updated 2 weeks ago
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆248Updated this week
- A library for efficient patching and automatic circuit discovery.☆99Dec 31, 2025Updated 7 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆60Jul 27, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- This repository collects all relevant resources about interpretability in LLMs☆404Nov 1, 2024Updated last year
- [EMNLP 2025 Demo] Extracting internal representations from vision-language models. Beta version.☆123Apr 25, 2026Updated 3 months ago
- Modified to support crosscoder training.☆27Jul 2, 2026Updated last month
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆105Nov 30, 2025Updated 8 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)☆28Jan 17, 2026Updated 6 months ago
- Open source interpretability artefacts for R1.☆183Apr 21, 2025Updated last year
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆91Jun 5, 2026Updated 2 months ago
- Localization of Knowledge in Text-to-Image Models☆11Oct 8, 2024Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆60Nov 3, 2024Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆303Jul 20, 2024Updated 2 years ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆247May 13, 2026Updated 3 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆898Mar 6, 2026Updated 5 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆17Apr 15, 2024Updated 2 years ago