Alternatives and similar repositories for r1-interpretability

Users that are interested in r1-interpretability are comparing it to the libraries listed below

• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆216Updated last year
• google-deepmind / mishax
  ☆144Updated 2 months ago
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆319Updated last month
• METR / RE-Bench
  ☆119Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆228Updated this week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆62Updated last year
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆234Updated 4 months ago
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆189Updated 8 months ago
• PrimeIntellect-ai / prime-environments
  Training-Ready RL Environments + Evals
  ☆182Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆151Updated 10 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆231Updated 11 months ago
• LeonGuertler / UnstableBaselines
  ☆106Updated last month
• emergent-misalignment / emergent-misalignment
  ☆229Updated this week
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆173Updated 10 months ago
• da03 / Internalize_CoT_Step_by_Step
  ☆199Updated 7 months ago
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆340Updated 3 weeks ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆150Updated 5 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆84Updated 8 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆194Updated last year
• SalesforceAIResearch / LaTRO
  ☆124Updated 9 months ago
• interp-reasoning / thought-anchors
  ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
  ☆92Updated last month
• neelnanda-io / Crosscoders
  ☆58Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆24Updated 11 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆281Updated 2 months ago
• jacobdunefsky / transcoder_circuits
  ☆189Updated last year
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆84Updated last year
• PrimeIntellect-ai / genesys
  ☆136Updated 8 months ago
• JackCai1206 / arithmetic-self-improve
  ☆37Updated 9 months ago
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆509Updated last week