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.
  ☆32Updated 2 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆123Updated 3 weeks ago
• oli-clive-griffin / crosscode
  A library for training crosscoders
  ☆15Updated 7 months ago
• noanabeshima / tinymodel
  A TinyStories LM with SAEs and transcoders
  ☆14Updated 9 months ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆107Updated last month
• HumanCompatibleAI / leela-interp
  Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"
  ☆26Updated last year
• nacloos / baba-is-ai
  Code for "Baba Is AI: Break the Rules to Beat the Benchmark"
  ☆41Updated 4 months ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆90Updated 2 years ago
• safety-research / safety-examples
  ☆24Updated 2 months ago
• quantified-uncertainty / ai-safety-papers
  ☆22Updated 4 years ago
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆17Updated last week
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆198Updated 2 years ago
• redwoodresearch / rust_circuit_public
  ☆66Updated 2 years ago
• neoneye / arc-notes
  My writings about ARC (Abstraction and Reasoning Corpus)
  ☆87Updated last month
• neelnanda-io / Neuroscope
  Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons
  ☆13Updated 2 years ago
• goodfire-ai / scribe
  ☆62Updated last week
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆21Updated last year
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆15Updated 3 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆132Updated 3 years ago
• callummcdougall / sae-exercises-mats
  ☆25Updated 2 years ago
• METR / public-tasks
  ☆116Updated 2 months ago
• mishajw / repeng
  Experiments with representation engineering
  ☆13Updated last year
• callummcdougall / sae_visualizer
  ☆29Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆237Updated 5 months ago
• aypan17 / machiavelli
  ☆144Updated 5 months ago
• science-of-finetuning / diffing-toolkit
  A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.
  ☆50Updated this week
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• jessicarumbelow / Backwards
  ☆85Updated last year
• neoneye / ARC-Interactive-History-Dataset
  The history files when recording human interaction while solving ARC tasks
  ☆118Updated last week
• young-geng / tpu_pod_commander
  TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.
  ☆21Updated 3 months ago