Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
☆198Mar 12, 2026Updated 3 months ago
Alternatives and similar repositories for axbench
Users that are interested in axbench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] General-purpose activation steering library☆174Sep 18, 2025Updated 8 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆883Mar 6, 2026Updated 3 months ago
- ☆18Mar 30, 2025Updated last year
- ☆218Oct 14, 2025Updated 8 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 7 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆34Nov 16, 2025Updated 6 months ago
- ☆19Sep 1, 2025Updated 9 months ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,569Mar 5, 2026Updated 3 months ago
- Sparsify transformers with SAEs and transcoders☆725Jun 8, 2026Updated last week
- 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…☆13Jan 26, 2025Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆53Nov 30, 2024Updated last year
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆263Sep 24, 2024Updated last year
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆25Aug 15, 2025Updated 10 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.
- Steering Llama 2 with Contrastive Activation Addition☆236May 23, 2024Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆955Updated this week
- A library for efficient patching and automatic circuit discovery.☆97Dec 31, 2025Updated 5 months ago
- ☆48Sep 29, 2024Updated last year
- Engine for collecting, uploading, and downloading model activations☆29Apr 2, 2025Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆594Aug 7, 2025Updated 10 months ago
- ☆422Aug 21, 2025Updated 9 months ago
- ☆250Nov 22, 2024Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆260Jun 8, 2026Updated last week
- 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.
- ☆32Nov 28, 2024Updated last year
- ☆289Oct 1, 2024Updated last year
- Open Source Replication of Anthropic's Alignment Faking Paper☆58Apr 4, 2025Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆151Feb 21, 2025Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆43Jan 18, 2026Updated 4 months ago
- ☆19Aug 19, 2025Updated 9 months ago
- A curated list of resources for activation engineering☆139Oct 2, 2025Updated 8 months ago
- ☆24Aug 30, 2025Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆1,419Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Mamba support for transformer lens☆20Sep 17, 2024Updated last year
- A resource repository for representation engineering in large language models☆153Nov 14, 2024Updated last year
- Codebase for Linguistic Collapse: Neural Collapse in (Large) Language Models [NeurIPS 2024] [arXiv:2405.17767]☆19Apr 14, 2025Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆240Mar 16, 2026Updated 3 months ago
- ☆37Jul 9, 2025Updated 11 months ago
- ☆54May 9, 2025Updated last year
- [ICLR 2025] FLAT: LLM Unlearning via Loss Adjustment with Only Forget Data☆14Feb 26, 2025Updated last year