Alternatives and similar repositories for superposition:

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

• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated 2 years ago
• srush / anynp
  Proof-of-concept of global switching between numpy/jax/pytorch in a library.
  ☆18Updated 10 months ago
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆57Updated last year
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆59Updated 3 years ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• Silent-Zebra / twisted-smc-lm
  ☆28Updated last month
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆62Updated 3 years ago
• shikaiqiu / compute-better-spent
  ☆53Updated 7 months ago
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years ago
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆35Updated 11 months ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆78Updated 2 years ago
• thestephencasper / everything-you-need
  we got you bro
  ☆35Updated 9 months ago
• callummcdougall / sae_visualizer
  ☆27Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• berlino / seq_icl
  ☆52Updated 11 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆61Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆114Updated 4 months ago
• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆36Updated last year
• irregular-rhomboid / EAI-Math-Reading-Group
  Resources from the EleutherAI Math Reading Group
  ☆53Updated 2 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆195Updated 2 months ago
• AllanYangZhou / universal_neural_functional
  ☆49Updated last year
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆35Updated 9 months ago
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆25Updated 6 months ago
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated this week
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated last year
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆19Updated 3 weeks ago
• yashbonde / rasp
  Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.
  ☆53Updated 3 years ago
• stanislavfort / dissect-git-re-basin
  Replicating and dissecting the git-re-basin project in one-click-replication Colabs
  ☆36Updated 2 years ago
• cloneofsimo / min-fsdp
  ☆78Updated 10 months ago
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆34Updated 6 months ago