Alternatives and similar repositories for superposition

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

• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆135Updated 3 years ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆186Updated 2 weeks ago
• cloneofsimo / min-fsdp
  ☆92Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆137Updated last year
• srush / do-we-need-attention
  ☆167Updated 2 years ago
• bilal-chughtai / rep-theory-mech-interp
  ☆28Updated 2 years ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆83Updated 3 years ago
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆76Updated 3 years ago
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 10 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆252Updated 3 weeks ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆113Updated 3 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• erfanzar / jax-flash-attn2
  A flexible and efficient implementation of Flash Attention 2.0 for JAX, supporting multiple backends (GPU/TPU/CPU) and platforms (Triton/…
  ☆34Updated 11 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆170Updated 6 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆92Updated 2 years ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆62Updated 4 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• berlino / seq_icl
  ☆53Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆62Updated 2 years ago
• srush / mamba-primer
  ☆39Updated last year
• yixiaoer / mistral-v0.2-jax
  JAX implementation of the Mistral 7b v0.2 model
  ☆35Updated last year
• princeton-nlp / TransformerPrograms
  [NeurIPS 2023] Learning Transformer Programs
  ☆162Updated last year
• 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
• 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
• davisyoshida / lorax
  LoRA for arbitrary JAX models and functions
  ☆144Updated last year
• xrsrke / pipegoose
  Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*
  ☆86Updated 2 years ago