quantified-uncertainty / ai-safety-papers

Related projects: ⓘ

• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆48Updated 2 years ago
• moirage / alignment-research-dataset
  A dataset of alignment research and code to reproduce it
  ☆68Updated last year
• apartresearch / readingwhatwecan
  📚📚📚📚📚📚📚📚📚 Reading everything
  ☆12Updated 4 months ago
• adamjermyn / toy_model_interpretability
  ☆10Updated last year
• JacobPfau / procgenAISC
  ☆18Updated last year
• jacobdunefsky / transcoder_circuits
  ☆33Updated 3 months ago
• anthropics / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆169Updated 2 years ago
• thestephencasper / everything-you-need
  we got you bro
  ☆32Updated last month
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆69Updated this week
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆88Updated 2 years ago
• samacqua / LARC
  Language-annotated Abstraction and Reasoning Corpus
  ☆76Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆18Updated last month
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆11Updated 2 years ago
• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆24Updated 3 weeks ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆182Updated this week
• callummcdougall / sae_visualizer
  ☆24Updated 5 months ago
• 4rtemi5 / imax
  Image augmentation library for Jax
  ☆36Updated 5 months ago
• alexander-turner / attainable-utility-preservation
  ☆12Updated 3 years ago
• EleutherAI / project-menu
  See the issue board for the current status of active and prospective projects!
  ☆65Updated 2 years ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆62Updated 10 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆59Updated last year
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆14Updated last month
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆14Updated last year
• EleutherAI / pyfra
  Python Research Framework
  ☆107Updated last year
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆13Updated 5 months ago
• RewardReports / reward-reports
  Documentation for dynamic machine learning systems.
  ☆26Updated last week
• neale / avoiding-side-effects
  Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments
  ☆12Updated 3 years ago
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆58Updated 2 years ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆57Updated 10 months ago
• DAIOS-AI / mindscript
  A programming language for formal/informal computation.
  ☆39Updated 3 months ago