A toolkit for embedding text datasets with sparse autoencoders
☆32Mar 24, 2026Updated 6 months ago
Alternatives and similar repositories for interp-embed
Users that are interested in interp-embed are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382☆97Jul 24, 2026Updated 2 months ago
- ADAG: Transluce's MLP neuron-level circuit tracing library☆41Apr 10, 2026Updated 5 months ago
- ☆140Updated this week
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆60Nov 3, 2024Updated last year
- Unified access to Large Language Model modules using NNsight☆121Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆15Jun 10, 2022Updated 4 years ago
- Official repo for the paper "Bilinear MLPs enable weight-based mechanistic interpretability".☆42Sep 20, 2026Updated 2 weeks ago
- Automated Qualitative Analysis of LLMs (ICLR 2025)☆54Jul 6, 2025Updated last year
- [NAACL 2025] Representing Rule-based Chatbots with Transformers☆23Feb 9, 2025Updated last year
- ☆74Jan 17, 2025Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆279Updated this week
- Code for Negation Neglect☆18May 22, 2026Updated 4 months ago
- AI Control for Claude Code in the real world☆34Sep 27, 2026Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,121Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- ☆33Jul 1, 2026Updated 3 months ago
- Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.☆16Apr 23, 2026Updated 5 months ago
- ☆51May 27, 2025Updated last year
- ☆18Sep 28, 2026Updated last week
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 5 months ago
- ☆13Aug 14, 2022Updated 4 years ago
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆29Nov 3, 2025Updated 11 months ago
- Codebase for Temporal SAEs paper☆27Nov 14, 2025Updated 10 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.
- ☆22Oct 22, 2023Updated 2 years ago
- ☆956Aug 2, 2026Updated 2 months ago
- A tool for calling (and calling out to) large language models.☆16Aug 13, 2024Updated 2 years ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆267Mar 16, 2026Updated 6 months ago
- Dataaset Release for Explanations for CommonsenseQA, ACL 2021 Paper☆21Jul 30, 2021Updated 5 years ago
- ☆19May 19, 2025Updated last year
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆88Updated this week
- ☆16Jan 2, 2026Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆1,551Updated this week
- 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.
- ↕️ Intuitive axiomatic retrieval experimentation.☆31Updated this week
- ☆16Jan 30, 2025Updated last year
- ☆41Jul 9, 2025Updated last year
- An R package for calculating effect size distributions in meta analyses☆19Jul 16, 2026Updated 2 months ago
- Implementation for IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs (ICLR 2026).☆25Jun 9, 2026Updated 4 months ago
- Code for Columbia University COMS 3997 – LLM Ethics and Foundations☆16Jan 7, 2025Updated last year
- ☆20Apr 10, 2025Updated last year