Alternatives and similar repositories for superposition

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

• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆186Updated 2 weeks ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆135Updated 3 years ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• srush / do-we-need-attention
  ☆167Updated 2 years ago
• cloneofsimo / min-fsdp
  ☆92Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆113Updated 2 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆137Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• yixiaoer / tpux
  A set of Python scripts that makes your experience on TPU better
  ☆56Updated 4 months ago
• bilal-chughtai / rep-theory-mech-interp
  ☆28Updated 2 years ago
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆88Updated last year
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆83Updated 3 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆76Updated 3 years ago
• 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 2 years ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆30Updated last year
• berlino / seq_icl
  ☆53Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆252Updated 3 weeks ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆198Updated last year
• AllanYangZhou / universal_neural_functional
  ☆55Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 10 months ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• yixiaoer / mistral-v0.2-jax
  JAX implementation of the Mistral 7b v0.2 model
  ☆35Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆46Updated 2 years ago
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆61Updated 3 years ago