Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.
☆12Nov 1, 2023Updated 3 years ago
Alternatives and similar repositories for easy-sae-training
Users that are interested in easy-sae-training are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- A quick way to get started with Transformer Lens☆15Dec 13, 2023Updated 2 years ago
- ☆26Aug 23, 2025Updated last year
- Applying SAEs for fine-grained control☆28Dec 15, 2024Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆11Jul 29, 2023Updated 3 years ago
- TransformerLens + HuggingFace☆11Nov 4, 2023Updated 3 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆17Apr 15, 2024Updated 2 years ago
- SAEs in Jax☆12Dec 16, 2024Updated last year
- Closed-form polynomial approximations to neural networks☆13Jan 31, 2025Updated last year
- Modified to support crosscoder training.☆29Jul 2, 2026Updated 4 months ago
- ☆26Jan 28, 2025Updated last year
- A library for activation patching based on nnsight.☆12May 27, 2025Updated last year
- minimal code to reproduce results from Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representati…☆14Sep 25, 2025Updated last year
- 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.
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆278Feb 27, 2026Updated 8 months ago
- ☆34Oct 20, 2026Updated 2 weeks ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆21Oct 24, 2025Updated last year
- Quickly empty a DynamoDB table☆13May 4, 2021Updated 5 years ago
- ☆18Jul 9, 2025Updated last year
- 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
- graphpatch is a library for activation patching on PyTorch neural network models.☆22Feb 11, 2025Updated last year
- Decoder only transformer, built from scratch with PyTorch☆34Oct 22, 2023Updated 3 years ago
- 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.
- A library for training crosscoders☆18May 28, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- Knex RDS Data API Client☆16May 11, 2021Updated 5 years ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- ☆17Feb 14, 2024Updated 2 years ago
- A lightweight Appsync client that signs requests for you - designed to be run server-side (e.g. on Lambdas)☆22Apr 19, 2024Updated 2 years ago
- ☆20Apr 10, 2025Updated last year
- ☆12Mar 9, 2025Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 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.
- Cookiecutter template for Coefficient projects.☆18Jul 19, 2024Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆373Apr 30, 2026Updated 6 months ago
- An experimental tool to explore GPT-3's "miraculous" ability not only to spell its own token strings (it being a "character blind" model)…☆12Oct 3, 2023Updated 3 years ago
- A task runner for VSC based on atom-build-oracle implementation☆11Jan 22, 2024Updated 2 years ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆74Jun 19, 2024Updated 2 years ago
- Universal Neurons in GPT2 Language Models☆31May 28, 2024Updated 2 years ago
- Generating, validating and running exploitable verifiable coding problems☆15Sep 30, 2026Updated last month