ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
☆342Jul 23, 2025Updated 7 months ago
Alternatives and similar repositories for ViT-Prisma
Users that are interested in ViT-Prisma are comparing it to the libraries listed below
Sorting:
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆836Updated this week
- Training Sparse Autoencoders on Language Models☆1,233Updated this week
- ☆273Oct 1, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,133Updated this week
- Mechanistic Interpretability Visualizations using React☆326Dec 18, 2024Updated last year
- ☆209Oct 14, 2025Updated 4 months ago
- ☆153Dec 30, 2025Updated 2 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆20May 29, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆90Dec 31, 2025Updated 2 months ago
- This repository collects all relevant resources about interpretability in LLMs☆390Nov 1, 2024Updated last year
- ☆396Aug 21, 2025Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆243Feb 23, 2026Updated last week
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆30Oct 27, 2025Updated 4 months ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 2 weeks ago
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆292Jul 20, 2024Updated last year
- 👋 Overcomplete is a Vision-based SAE Toolbox☆123Dec 4, 2025Updated 3 months ago
- Open source interpretability artefacts for R1.☆172Apr 21, 2025Updated 10 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆183Sep 26, 2025Updated 5 months ago
- ☆79Nov 5, 2024Updated last year
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 8 months ago
- ☆140Aug 4, 2024Updated last year
- Modified to support crosscoder training.☆25Feb 4, 2026Updated last month
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆863Jan 29, 2026Updated last month
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆83Feb 25, 2025Updated last year
- ☆30Aug 2, 2024Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- ☆960Updated this week
- Unified access to Large Language Model modules using NNsight☆93Updated this week
- PyTorch-based library for various kinds of representational-similarity analysis☆24Jun 7, 2024Updated last year
- A toolkit for quantitative evaluation of data attribution methods.☆56Jul 14, 2025Updated 7 months ago
- ☆199Nov 17, 2024Updated last year
- ☆100Aug 8, 2024Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆28May 4, 2023Updated 2 years ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆57Nov 3, 2024Updated last year