Sparsify transformers with SAEs and transcoders
☆744Nov 16, 2026Updated this week
Alternatives and similar repositories for sparsify
Users that are interested in sparsify are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Training Sparse Autoencoders on Language Models☆1,588Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆283Updated this week
- ☆435Aug 21, 2025Updated last year
- ☆610Jul 19, 2024Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆278Feb 27, 2026Updated 8 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆186May 1, 2026Updated 6 months ago
- ☆225Oct 14, 2025Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆309Jul 20, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆4,083Updated this week
- ☆215Nov 17, 2024Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,151Updated this week
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods☆233Oct 4, 2026Updated last month
- ☆113Nov 10, 2026Updated last 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.
- Using sparse coding to find distributed representations used by neural networks.☆316Nov 10, 2023Updated 3 years ago
- ☆158Oct 30, 2026Updated 2 weeks ago
- ☆142Oct 28, 2023Updated 3 years ago
- ☆26Aug 23, 2025Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆94Nov 27, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆920Mar 6, 2026Updated 8 months ago
- ☆302Oct 1, 2024Updated 2 years ago
- ☆62Nov 19, 2024Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆379Apr 30, 2026Updated 6 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.
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆67Jul 24, 2025Updated last year
- ☆2,960Oct 14, 2026Updated last month
- ☆26Jan 28, 2025Updated last year
- ☆32Apr 4, 2024Updated 2 years ago
- Sparsify transformers with cross-layer transcoders☆27Nov 14, 2025Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated 2 years ago
- This repository collects all relevant resources about interpretability in LLMs☆414Nov 1, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆400Oct 7, 2026Updated last month
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆90Jun 20, 2026Updated 4 months ago
- Open source interpretability artefacts for R1.☆187Apr 21, 2025Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆622Aug 7, 2025Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- Sparse probing paper full code.☆70Dec 17, 2023Updated 2 years ago
Are these results useful?