Open-source release accompanying Gao et al. 2025
☆531Dec 11, 2025Updated 8 months ago
Alternatives and similar repositories for circuit_sparsity
Users that are interested in circuit_sparsity are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆16May 25, 2026Updated 3 months ago
- ☆2,899Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆275Aug 25, 2026Updated last week
- ☆18Jul 9, 2025Updated last year
- Official PyTorch Implementation for Learning a Generative Meta-Model of LLM Activations, ICML 2026☆94Apr 30, 2026Updated 4 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.
- Parameter Decomposition☆140Aug 24, 2026Updated last week
- Sparsify transformers with SAEs and transcoders☆739Updated this week
- ☆428Aug 21, 2025Updated last year
- Official code release for Delta Activations: A Representation for Finetuned Large Language Models☆21Sep 5, 2025Updated 11 months ago
- Training Sparse Autoencoders on Language Models☆1,518Updated this week
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆360Aug 21, 2026Updated last week
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- NanoGPT (124M) in 90 seconds☆5,723Aug 9, 2026Updated 3 weeks ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Repo du cours d'introduction à l'apprentissage par renforcement.☆19Feb 2, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,083Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,837Updated this week
- ☆111May 23, 2026Updated 3 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆752Updated this week
- open source interpretability platform 🧠☆1,122Updated this week
- Open source interpretability artefacts for R1.☆183Apr 21, 2025Updated last year
- Official Project Page for Deep Delta Learning (https://arxiv.org/abs/2601.00417)☆356Jul 27, 2026Updated last month
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated 11 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.
- ☆26Aug 23, 2025Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- Kernels, of the mega variety :)☆816May 26, 2026Updated 3 months ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Jul 6, 2026Updated last month
- Renderer for the harmony response format to be used with gpt-oss☆4,494Apr 8, 2026Updated 4 months ago
- Muon is an optimizer for hidden layers in neural networks☆2,815May 24, 2026Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆274Feb 27, 2026Updated 6 months ago
- Unified access to Large Language Model modules using NNsight☆119Updated this week
- ☆211Nov 17, 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.
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models☆4,634Jan 14, 2026Updated 7 months ago
- A suite of interpretability tasks to evaluate agents using Scribe for notebook access☆18Oct 2, 2025Updated 10 months ago
- Our library for RL environments + evals☆4,577Updated this week
- A codebase for pretraining multi-billion-scale sparse GPTs.☆28Feb 9, 2026Updated 6 months ago
- ☆228Jan 5, 2026Updated 7 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆676Mar 21, 2026Updated 5 months ago
- Auditing agents for fine-tuning safety☆22Oct 21, 2025Updated 10 months ago