☆162May 1, 2026Updated this week
Alternatives and similar repositories for SAEBench
Users that are interested in SAEBench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆25Aug 23, 2025Updated 8 months ago
- Training Sparse Autoencoders on Language Models☆1,361Updated this week
- Sparsify transformers with SAEs and transcoders☆714Apr 27, 2026Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆253Apr 27, 2026Updated last week
- ☆412Aug 21, 2025Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Sparse Autoencoder Training Library☆56May 1, 2025Updated last year
- ☆100Updated this week
- ☆28Nov 28, 2024Updated 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…☆13Jan 26, 2025Updated last year
- ☆24Jan 28, 2025Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆256Feb 27, 2026Updated 2 months ago
- ☆64Jan 17, 2025Updated last year
- ☆22Feb 13, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Open source replication of Anthropic's Crosscoders for Model Diffing☆65Oct 27, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆302Nov 10, 2023Updated 2 years ago
- Engine for collecting, uploading, and downloading model activations☆28Apr 2, 2025Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆917Updated this week
- A library for efficient patching and automatic circuit discovery.☆97Dec 31, 2025Updated 4 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆213Oct 14, 2025Updated 6 months ago
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 6 months 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.
- ☆38Apr 30, 2024Updated 2 years ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆214Updated this week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆585Jul 19, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,383Apr 30, 2026Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆296Jul 20, 2024Updated last year
- Mapping out the "memory" of neural nets with data attribution☆54Updated this week
- Sparse probing paper full code.☆67Dec 17, 2023Updated 2 years ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- 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.
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆30May 23, 2024Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 3 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆17Dec 15, 2024Updated last year
- Applying SAEs for fine-grained control☆26Dec 15, 2024Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆356Jul 23, 2025Updated 9 months ago
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"☆30Apr 22, 2026Updated 2 weeks ago
- ☆29Apr 4, 2024Updated 2 years ago