Alternatives and similar repositories for minSAE

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

• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 11 months ago
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆103Updated 2 months ago
• cloneofsimo / ezmup
  Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
  ☆85Updated last year
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆57Updated 8 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 11 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆174Updated 5 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 9 months ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• ethansmith2000 / TransformerExperiments
  ☆19Updated 6 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆197Updated last year
• test-time-training / ttt-tk
  ☆41Updated last month
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆64Updated last month
• main-horse / hnet-old
  H-Net Dynamic Hierarchical Architecture
  ☆80Updated 2 months ago
• apple / ml-ademamix
  ☆68Updated last year
• LIONS-EPFL / scion
  ☆48Updated last month
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆276Updated 3 weeks ago
• nikhilvyas / SOAP
  ☆224Updated last year
• dvruette / gidd
  Code accompanying the paper "Generalized Interpolating Discrete Diffusion"
  ☆108Updated 5 months ago
• berlino / seq_icl
  ☆53Updated last year
• zaydzuhri / softpick-attention
  Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"
  ☆85Updated 2 months ago
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆23Updated 5 months ago
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆50Updated last year
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆192Updated last year
• CLAIRE-Labo / flash_attention
  A basic pure pytorch implementation of flash attention
  ☆16Updated last year
• Laz4rz / mup
  Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation
  ☆14Updated 6 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• JesseFarebro / flax-mup
  Maximal Update Parametrization (μP) with Flax & Optax.
  ☆16Updated last year