Alternatives and similar repositories for grokking

Users that are interested in grokking are comparing it to the libraries listed below

• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆83Updated 3 years ago
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆62Updated 2 years ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆113Updated 3 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆198Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆89Updated last year
• DeqingFu / transformers-icl-second-order
  Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…
  ☆19Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆93Updated 2 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated 2 years ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆186Updated 3 weeks ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆46Updated 2 years ago
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 10 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆138Updated last year
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆41Updated last year
• srush / do-we-need-attention
  ☆167Updated 2 years ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆30Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆135Updated 3 years ago
• adamkarvonen / SAE_BoardGameEval
  ☆24Updated last year
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆99Updated last year
• GFNOrg / gfn-lm-tuning
  ☆185Updated 2 years ago
• gregorbachmann / Next-Token-Failures
  ☆108Updated last year
• lee-ny / teaching_arithmetic
  ☆84Updated 2 years ago
• katiekang1998 / reasoning_generalization
  ☆33Updated last year
• AllanYangZhou / universal_neural_functional
  ☆55Updated last year
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆90Updated 2 years ago
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆78Updated 3 years ago
• formll / dog
  DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
  ☆64Updated 2 years ago
• oripress / AlgoTune
  AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each…
  ☆88Updated last week
• ejnnr / cupbearer
  A library for mechanistic anomaly detection
  ☆22Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆28Updated 2 years ago