Alternatives and similar repositories for grokking

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

• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆221Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆75Updated 2 years ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆239Updated 10 months ago
• serre-lab / Lens
  LENS Project
  ☆51Updated last year
• jessicarumbelow / Backwards
  ☆85Updated last year
• CentreSecuriteIA / BELLS
  Benchmarks for the Evaluation of LLM Supervision
  ☆32Updated last month
• bremen79 / parameterfree
  Parameter-Free Optimizers for Pytorch
  ☆130Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆546Updated 3 months ago
• KindXiaoming / BIMT
  Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
  ☆174Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆302Updated 11 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆114Updated 5 months ago
• YuhangSong / Prospective-Configuration
  This repository contains the code for the paper "Inferring Neural Activity Before Plasticity: A Foundation for Learning Beyond Backpropag…
  ☆139Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆211Updated last year
• rbardenet / bml-course
  Public repo for course material on Bayesian machine learning at ENS Paris-Saclay and Univ Lille
  ☆92Updated 9 months ago
• FrankVeenstra / EvolvingModularRobots_Unity
  Software for Evolving Modular Robots in Unity
  ☆20Updated 8 months ago
• cbg-ethz / bmi
  Mutual information estimators and benchmark
  ☆54Updated 2 months ago
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆833Updated last month
• ellisk42 / humanlike_fewshot_learning
  ☆30Updated 2 years ago
• sambowyer / bayes_evals
  A lightweight library for Bayesian analysis of LLM evals (ICML 2025 Spotlight Position Paper)
  ☆21Updated 6 months ago
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆323Updated 4 months ago
• Atcold / Energy-Book
  Deep Learning, an Energy Approach
  ☆222Updated 5 months ago
• mlco2 / impact
  ML has an impact on the climate. But not all models are born equal. Compute your model's emissions with our calculator and add the result…
  ☆244Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆232Updated 3 months ago
• benchopt / benchopt
  Making your benchmark of optimization algorithms simple and open
  ☆275Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆228Updated 11 months ago
• google-deepmind / tracr
  ☆548Updated last year
• chr5tphr / zennit
  Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
  ☆236Updated 4 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆191Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆130Updated 3 years ago
• marikgoldstein / slides
  ☆18Updated last year