neelnanda-io / Grokking

Related projects ⓘ

Alternatives and complementary repositories for Grokking

• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆64Updated 2 years ago
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆51Updated last year
• jacobdunefsky / transcoder_circuits
  ☆44Updated last week
• EleutherAI / sae-auto-interp
  ☆109Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆63Updated last year
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆34Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆109Updated last year
• KindXiaoming / BIMT
  Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
  ☆163Updated last year
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• Lemon-cmd / energy-transformer-graph
  This repository contains the official code for Energy Transformer---an efficient Energy-based Transformer variant for graph classificatio…
  ☆20Updated 9 months ago
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆13Updated 7 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆200Updated 4 months ago
• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆34Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆97Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆180Updated 5 months ago
• probcomp / LLaMPPL
  A domain-specific probabilistic programming language for modeling and inference with language models
  ☆112Updated last year
• thestephencasper / everything-you-need
  we got you bro
  ☆33Updated 3 months ago
• saprmarks / dictionary_learning
  ☆146Updated last month
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆27Updated 5 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆77Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆161Updated last month
• berlino / seq_icl
  ☆50Updated 6 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆95Updated 6 months ago
• adamjermyn / toy_model_interpretability
  ☆11Updated 2 years ago
• probcomp / hfppl
  Probabilistic programming with HuggingFace language models
  ☆89Updated this week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆189Updated 4 months ago
• KihoPark / linear_rep_geometry
  ☆76Updated 9 months ago