stanfordnlp / axbenchView external linksLinks
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
☆163Jun 25, 2025Updated 7 months ago
Alternatives and similar repositories for axbench
Users that are interested in axbench are comparing it to the libraries listed below
Sorting:
- ☆207Oct 14, 2025Updated 4 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆858Jan 29, 2026Updated 2 weeks ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆24Aug 15, 2025Updated 5 months ago
- ☆16Sep 1, 2025Updated 5 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 3 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆49Sep 22, 2025Updated 4 months ago
- [ICLR 2025] General-purpose activation steering library☆141Sep 18, 2025Updated 4 months ago
- Engine for collecting, uploading, and downloading model activations☆26Apr 2, 2025Updated 10 months ago
- ☆28Nov 16, 2025Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆88Dec 31, 2025Updated last month
- ☆25Nov 28, 2024Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- Sparsify transformers with SAEs and transcoders☆692Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆811Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆207May 23, 2024Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆51Nov 30, 2024Updated last year
- ☆267Oct 1, 2024Updated last year
- Measuring if attention is explanation with ROAR☆22Mar 3, 2023Updated 2 years ago
- ☆389Aug 21, 2025Updated 5 months ago
- Open Source Replication of Anthropic's Alignment Faking Paper☆54Apr 4, 2025Updated 10 months ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,555Jan 14, 2026Updated last month
- ☆230Nov 22, 2024Updated last year
- ☆17Aug 30, 2025Updated 5 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆146Dec 30, 2025Updated last month
- 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…☆12Jan 26, 2025Updated last year
- ☆21Jul 21, 2025Updated 6 months ago
- Training Sparse Autoencoders on Language Models☆1,201Updated this week
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- ☆25Dec 20, 2023Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆567Aug 7, 2025Updated 6 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆42Jan 18, 2026Updated 3 weeks ago
- ☆83Feb 25, 2025Updated 11 months ago
- ☆27Oct 6, 2024Updated last year
- [ACL 2025] Knowledge Unlearning for Large Language Models☆48Sep 18, 2025Updated 4 months ago
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆25Nov 3, 2025Updated 3 months ago
- ☆19Aug 4, 2025Updated 6 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆228Dec 12, 2025Updated 2 months ago