Open source interpretability artefacts for R1.
☆186Apr 21, 2025Updated last year
Alternatives and similar repositories for r1-interpretability
Users that are interested in r1-interpretability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆51May 27, 2025Updated last year
- Ember is a hosted API/SDK that lets you shape AI model behavior by directly controlling a model's internal units of computation, or "feat…☆55Jul 14, 2025Updated last year
- Parameter Decomposition☆153Oct 20, 2026Updated 2 weeks ago
- ☆91Feb 18, 2026Updated 8 months ago
- So, I trained a MoE based a 124M (8x12M) architecture I coded from ground up to build a small instruct model, going through the below-men…☆14Jul 18, 2025Updated 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.
- Training Sparse Autoencoders on Language Models☆1,579Oct 20, 2026Updated 2 weeks ago
- ☆435Aug 21, 2025Updated last year
- ☆42Jul 9, 2025Updated last year
- ☆29Nov 6, 2025Updated 11 months ago
- Sparsify transformers with SAEs and transcoders☆742Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated 2 years ago
- Code repo for the model organisms and convergent directions of EM papers.☆90Sep 22, 2025Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆19Jul 6, 2026Updated 3 months ago
- Unified access to Large Language Model modules using NNsight☆121Oct 27, 2026Updated last week
- 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.
- ☆14Oct 6, 2026Updated 3 weeks ago
- Modified to support crosscoder training.☆29Jul 2, 2026Updated 4 months ago
- ☆214Nov 17, 2024Updated last year
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 3 years ago
- ☆2,938Oct 14, 2026Updated 2 weeks ago
- ☆99Mar 28, 2025Updated last year
- A library for training crosscoders☆18May 28, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆4,031Updated this week
- ☆143Oct 24, 2026Updated last week
- 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.
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Jul 8, 2026Updated 3 months ago
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆277Feb 27, 2026Updated 8 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Oct 11, 2026Updated 3 weeks ago
- Dataset Generation Code for SimpleStories☆12Dec 19, 2025Updated 10 months ago
- The official implementation of "Interpreting the repeated token phenomenon in LLMs"☆15Sep 23, 2025Updated last year
- ☆225Oct 14, 2025Updated last year
- ☆126Sep 30, 2026Updated last month
- 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.
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆280Updated this week
- open source interpretability platform 🧠☆1,198Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,138Updated this week
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods☆232Oct 4, 2026Updated last month
- Mechanistic Interpretability Visualizations using React☆372Apr 30, 2026Updated 6 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆270Mar 16, 2026Updated 7 months ago