Alternatives and similar repositories for structured-representations-maze-transformers

Users that are interested in structured-representations-maze-transformers are comparing it to the libraries listed below

• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆31Updated last year
• safety-research / safety-examples
  ☆20Updated 2 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆101Updated 2 months ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆87Updated last year
• noanabeshima / tinymodel
  A TinyStories LM with SAEs and transcoders
  ☆13Updated 4 months ago
• HumanCompatibleAI / leela-interp
  Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"
  ☆25Updated last year
• nacloos / baba-is-ai
  ☆39Updated 11 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆188Updated 2 years ago
• Avalon-Benchmark / avalon
  A 3D video game environment and benchmark designed from scratch for reinforcement learning research
  ☆188Updated 2 years ago
• amack315 / unsupervised-steering-vectors
  ☆33Updated last year
• neoneye / ARC-Interactive-History-Dataset
  The history files when recording human interaction while solving ARC tasks
  ☆114Updated last week
• neoneye / arc-notes
  My writings about ARC (Abstraction and Reasoning Corpus)
  ☆82Updated 2 weeks ago
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆12Updated last month
• mishajw / repeng
  Experiments with representation engineering
  ☆12Updated last year
• luchris429 / JaxLife
  An Open-Ended Agentic Simulator
  ☆52Updated last year
• cogment / cogment-lab
  A toolkit for practical Human-AI cooperation research
  ☆14Updated last year
• jannik-brinkmann / hugginglens
  TransformerLens + HuggingFace
  ☆11Updated last year
• young-geng / tpu_pod_commander
  TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.
  ☆20Updated last year
• delphi-suite / delphi
  small language models training made easy
  ☆13Updated 8 months ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆93Updated 5 months ago
• balrog-ai / BALROG
  Benchmarking Agentic LLM and VLM Reasoning On Games
  ☆185Updated last week
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆79Updated 3 years ago
• amacati / SoulsGym
  Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games
  ☆136Updated 10 months ago
• facebookresearch / motif
  Intrinsic Motivation from Artificial Intelligence Feedback
  ☆131Updated last year
• huggingface / simulate
  🎢 Creating and sharing simulation environments for embodied and synthetic data research
  ☆191Updated last year
• jennyzzt / awesome-open-ended
  Awesome Open-ended AI
  ☆333Updated 3 weeks ago
• NetHack-LE / nle
  The NetHack Learning Environment
  ☆87Updated last week
• Kinds-of-Intelligence-CFI / animal-ai
  Animal-AI supports interdisciplinary research to help better understand human, animal, and artificial cognition.
  ☆75Updated 2 months ago
• understanding-search / maze-dataset
  maze datasets for investigating OOD behavior of ML systems
  ☆53Updated last week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆209Updated this week