Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
☆67Jul 24, 2025Updated 11 months ago
Alternatives and similar repositories for BatchTopK
Users that are interested in BatchTopK are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆427Aug 21, 2025Updated 11 months ago
- Modified to support crosscoder training.☆27Jul 2, 2026Updated 2 weeks ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- ☆72Jan 17, 2025Updated last year
- Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)☆28Jan 17, 2026Updated 6 months 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.
- ☆595Jul 19, 2024Updated 2 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- ☆109May 23, 2026Updated last month
- Sparsify transformers with SAEs and transcoders☆732Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆266Jul 13, 2026Updated last week
- ☆24Feb 13, 2026Updated 5 months ago
- Using sparse coding to find distributed representations used by neural networks.☆306Nov 10, 2023Updated 2 years ago
- Code for the paper "A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders"☆15Dec 28, 2025Updated 6 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.
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆265Feb 27, 2026Updated 4 months ago
- ☆177May 1, 2026Updated 2 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆34Sep 18, 2025Updated 10 months ago
- KV cache compression via sparse coding☆17Oct 26, 2025Updated 8 months ago
- The official repo for the Dialz Python library - a toolkit for steering vector research.☆27Mar 26, 2026Updated 3 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆210Mar 12, 2026Updated 4 months ago
- ☆33Nov 28, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- ☆26Dec 20, 2023Updated 2 years 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.
- Tools for exploring Transformer neuron behaviour, including input pruning and diversification.☆10Jun 6, 2023Updated 3 years ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆147Dec 4, 2025Updated 7 months ago
- Engine for collecting, uploading, and downloading model activations☆30Apr 2, 2025Updated last year
- ☆223Oct 14, 2025Updated 9 months ago
- James' cookbook of evaluations and finetuning experiments☆32Feb 19, 2026Updated 5 months ago
- My PhD manuscript LaTeX code and the slides for the defense☆11Feb 2, 2022Updated 4 years ago
- [ICASSP 2025] AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder☆14Mar 11, 2025Updated last year
- Learning to Skip the Middle Layers of Transformers☆17Aug 7, 2025Updated 11 months ago
- Codebase for Temporal SAEs paper☆24Nov 14, 2025Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- (WIP) A benchmark to see how well AI agents autonomously make money.☆15Jul 17, 2025Updated last year
- Investigating Cultural Alignment of Large Language Models☆13Aug 14, 2024Updated last year
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆79Jun 23, 2025Updated last year
- Sparsify transformers with cross-layer transcoders☆26Nov 14, 2025Updated 8 months ago
- Official repository for Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning☆12Sep 2, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆28Nov 20, 2024Updated last year