Alternatives and similar repositories for Grokking

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

• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆74Updated 5 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• neelnanda-io / Neuroscope
  Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons
  ☆12Updated 2 years ago
• callummcdougall / sae_visualizer
  ☆27Updated last year
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆78Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆188Updated 11 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆35Updated 9 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆50Updated 2 years ago
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated 2 years ago
• harmonic-ai / datasets
  Harmonic Datasets
  ☆39Updated 10 months ago
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆14Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆115Updated 5 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 7 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆131Updated 3 weeks ago
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆35Updated 9 months ago
• JackCai1206 / arithmetic-self-improve
  ☆29Updated 3 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆94Updated 3 months ago
• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆36Updated last year
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 11 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆29Updated 11 months ago
• google-deepmind / mishax
  ☆129Updated last month
• wattenberg / superposition
  Code associated to papers on superposition (in ML interpretability)
  ☆28Updated 2 years ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆49Updated 2 weeks ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆120Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆201Updated 5 months ago
• jbloomAus / SAEDashboard
  ☆38Updated 2 weeks ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆122Updated 2 years ago
• blei-lab / circuitry
  ☆13Updated 6 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆89Updated 3 months ago