PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
☆20Jan 19, 2025Updated last year
Alternatives and similar repositories for atp_star
Users that are interested in atp_star are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆29Nov 20, 2024Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- ☆20Apr 10, 2025Updated last year
- Mamba support for transformer lens☆20Sep 17, 2024Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- ☆15May 27, 2025Updated last year
- see github.com/understanding-search/maze-transformer☆10Dec 8, 2023Updated 2 years ago
- Modified to support crosscoder training.☆27Jul 2, 2026Updated last month
- REBUS: A Robust Evaluation Benchmark of Understanding Symbols☆13Aug 13, 2024Updated 2 years 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.
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- Implementation of path patching & activation patching (will eventually add to TransformerLens).☆15Jan 8, 2024Updated 2 years ago
- ☆12Jul 8, 2024Updated 2 years ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Jul 8, 2026Updated 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…☆14Jan 26, 2025Updated last year
- ☆16Nov 14, 2025Updated 9 months ago
- Engine for collecting, uploading, and downloading model activations☆30Apr 2, 2025Updated last year
- A curated reading list of research in Sparse Autoencoders, Feature Extraction and related topics in Mechanistic Interpretability☆33Jan 30, 2025Updated last year
- ☆67Feb 16, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆24Jun 30, 2025Updated last year
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆79Jul 20, 2026Updated 3 weeks ago
- Unified access to Large Language Model modules using NNsight☆119Jul 28, 2026Updated 2 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆48May 31, 2024Updated 2 years ago
- ☆429Aug 21, 2025Updated 11 months ago
- ☆86Feb 25, 2025Updated last year
- ☆294Oct 1, 2024Updated last year
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code☆11Aug 29, 2023Updated 2 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆269Feb 27, 2026Updated 5 months ago
- ☆24Apr 20, 2024Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- ☆18Updated this week
- ☆22Apr 22, 2024Updated 2 years ago
- A library for training crosscoders☆18May 28, 2025Updated last year
- ☆18Jul 9, 2025Updated last year