The nnsight package enables interpreting and manipulating the internals of deep learned models.
☆971Jun 29, 2026Updated last week
Alternatives and similar repositories for nnsight
Users that are interested in nnsight are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆425Aug 21, 2025Updated 10 months ago
- Training Sparse Autoencoders on Language Models☆1,442Jun 24, 2026Updated last week
- A library for mechanistic interpretability of GPT-style language models☆3,603Jun 27, 2026Updated last week
- Mechanistic Interpretability Visualizations using React☆353Apr 30, 2026Updated 2 months ago
- ☆219Oct 14, 2025Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The NDIF server, which performs deep inference and serves nnsight requests remotely☆47Jun 26, 2026Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆262Feb 27, 2026Updated 4 months ago
- ☆290Oct 1, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆888Mar 6, 2026Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆729Jun 22, 2026Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆262Updated this week
- ☆174May 1, 2026Updated 2 months ago
- ☆1,146Jun 22, 2026Updated last week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆370Jul 23, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Using sparse coding to find distributed representations used by neural networks.☆307Nov 10, 2023Updated 2 years ago
- Sparse Autoencoder Training Library☆57May 1, 2025Updated last year
- Unified access to Large Language Model modules using NNsight☆114May 6, 2026Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆302Jul 20, 2024Updated last year
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆598Aug 7, 2025Updated 10 months ago
- ☆253Feb 22, 2024Updated 2 years ago
- Modified to support crosscoder training.☆27Updated this week
- ☆139Oct 28, 2023Updated 2 years 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.
- Steering vectors for transformer language models in Pytorch / Huggingface☆153Feb 21, 2025Updated last year
- ☆590Jul 19, 2024Updated last year
- ☆80May 23, 2026Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆246Mar 16, 2026Updated 3 months ago
- ☆213Nov 17, 2024Updated last year
- ☆111Aug 8, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- ☆11Sep 23, 2024Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆198Apr 30, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆85Feb 18, 2026Updated 4 months ago
- ☆59Nov 19, 2024Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆239May 23, 2024Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆17Apr 15, 2024Updated 2 years ago
- open source interpretability platform 🧠☆932Jun 17, 2026Updated 2 weeks ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆205Mar 12, 2026Updated 3 months ago
- ☆107May 23, 2026Updated last month