Alternatives and similar repositories for neuronpedia

Users that are interested in neuronpedia are comparing it to the libraries listed below

• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆163Updated 6 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆214Updated last year
• safety-research / persona_vectors
  Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  ☆284Updated 3 months ago
• emergent-misalignment / emergent-misalignment
  ☆226Updated 2 weeks ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆654Updated last week
• decoderesearch / SAELens
  Training Sparse Autoencoders on Language Models
  ☆1,047Updated this week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆284Updated this week
• anthropics / attribution-graphs-frontend
  https://transformer-circuits.pub/2025/attribution-graphs/methods.html
  ☆90Updated 7 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆299Updated 5 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆697Updated this week
• openai / sparse_autoencoder
  ☆543Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆301Updated 11 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆225Updated last week
• safety-research / circuit-tracer
  ☆2,432Updated 2 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆227Updated 11 months ago
• jbloomAus / SAEDashboard
  ☆79Updated last month
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆128Updated this week
• anthropic-experimental / agentic-misalignment
  ☆520Updated 5 months ago
• jacobdunefsky / transcoder_circuits
  ☆188Updated last year
• aw31 / openai-imo-2025-proofs
  ☆478Updated 4 months ago
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆311Updated 3 weeks ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• PrimeIntellect-ai / prime-environments
  Training-Ready RL Environments + Evals
  ☆174Updated this week
• arcprize / arc-agi-benchmarking
  Testing baseline LLMs performance across various models
  ☆317Updated last week
• google-deepmind / mishax
  ☆143Updated 2 months ago
• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆573Updated 3 months ago
• SWE-bench / SWE-smith
  [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
  ☆451Updated last week
• METR / task-standard
  METR Task Standard
  ☆167Updated 9 months ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆847Updated last month
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆828Updated last month