Sea-Snell / grokking

Related projects ⓘ

Alternatives and complementary repositories for grokking

• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆34Updated last year
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆49Updated last year
• locuslab / edge-of-stability
  ☆59Updated 3 years ago
• ejmichaud / grokking-squared
  ☆22Updated last year
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆77Updated last year
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆57Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆54Updated 2 years ago
• google-research / jax-influence
  ☆58Updated 2 years ago
• epfml / llm-baselines
  NanoGPT-like codebase for LLM training
  ☆75Updated this week
• KihoPark / linear_rep_geometry
  ☆76Updated 9 months ago
• teddykoker / grokking
  PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆32Updated 2 years ago
• yilundu / irem_code_release
  ICML 2022: Learning Iterative Reasoning through Energy Minimization
  ☆43Updated last year
• berlino / seq_icl
  ☆50Updated 6 months ago
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆104Updated 3 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆55Updated 9 months ago
• andyljones / boardlaw
  Scaling scaling laws with board games.
  ☆41Updated last year
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆26Updated 2 weeks ago
• AllanYangZhou / universal_neural_functional
  ☆48Updated 9 months ago
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆58Updated 3 years ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆73Updated last year
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆60Updated 2 years ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆27Updated 5 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆79Updated 9 months ago
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• krandiash / quinine
  A library to create and manage configuration files, especially for machine learning projects.
  ☆77Updated 2 years ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• saprmarks / feature-circuits
  ☆105Updated last month
• GFNOrg / gfn-lm-tuning
  ☆127Updated 10 months ago
• twitter-research / hyperbolic-rl
  ☆56Updated 2 years ago