Alternatives and similar repositories for grokking

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

• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆286Updated last year
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆838Updated 2 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• google-research / optformer
  ☆232Updated 2 weeks ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆221Updated last year
• google-deepmind / tracr
  ☆549Updated last year
• aangelopoulos / ppi_py
  A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.
  ☆269Updated 3 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆117Updated 5 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆554Updated 4 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆673Updated this week
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆234Updated 4 months ago
• normal-computing / posteriors
  Uncertainty quantification with PyTorch
  ☆377Updated 2 months ago
• annahedstroem / MetaQuantus
  MetaQuantus is an XAI performance tool to identify reliable evaluation metrics
  ☆40Updated last year
• saprmarks / dictionary_learning
  ☆370Updated 4 months ago
• YuhangSong / Prospective-Configuration
  This repository contains the code for the paper "Inferring Neural Activity Before Plasticity: A Foundation for Learning Beyond Backpropag…
  ☆140Updated last year
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆239Updated 10 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆304Updated last year
• CentreSecuriteIA / BELLS
  Benchmarks for the Evaluation of LLM Supervision
  ☆32Updated 2 months ago
• bremen79 / parameterfree
  Parameter-Free Optimizers for Pytorch
  ☆130Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆232Updated last year
• wilson-labs / cola
  Compositional Linear Algebra
  ☆503Updated 4 months ago
• ironjr / grokfast
  Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
  ☆565Updated last year
• genlm / llamppl
  Probabilistic programming with large language models
  ☆154Updated last month
• GilpinLab / dysts
  Hundreds of strange attractors
  ☆506Updated 3 weeks ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆260Updated last year
• benchopt / benchopt
  Making your benchmark of optimization algorithms simple and open
  ☆282Updated this week
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆327Updated 4 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• srush / annotated-s4
  Implementation of https://srush.github.io/annotated-s4
  ☆509Updated 6 months ago
• bayesflow-org / bayesflow
  A Python library for amortized Bayesian workflows using generative neural networks.
  ☆622Updated last week