Alternatives and similar repositories for task_vectors:

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

• prateeky2806 / ties-merging
  ☆166Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆474Updated 8 months ago
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆95Updated last year
• davidbau / baukit
  ☆190Updated 11 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆213Updated last year
• EnnengYang / Awesome-Model-Merging-Methods-Theories-Applications
  Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.
  ☆316Updated this week
• microsoft / rho
  Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
  ☆398Updated 10 months ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆138Updated 4 months ago
• openai / sparse_autoencoder
  ☆421Updated 7 months ago
• roeehendel / icl_task_vectors
  ☆89Updated last year
• locuslab / massive-activations
  Code accompanying the paper "Massive Activations in Large Language Models"
  ☆140Updated 11 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆464Updated this week
• koayon / awesome-adaptive-computation
  A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).
  ☆139Updated last month
• likenneth / honest_llama
  Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  ☆499Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆182Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆116Updated last year
• soniajoseph / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).
  ☆205Updated this week
• mmatena / model_merging
  ☆64Updated 2 years ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆205Updated 4 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆216Updated 7 months ago
• collin-burns / discovering_latent_knowledge
  ☆262Updated 11 months ago
• lucidrains / st-moe-pytorch
  Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
  ☆306Updated 8 months ago
• dtsip / in-context-learning
  ☆211Updated 9 months ago
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆462Updated last year
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆104Updated 8 months ago
• KihoPark / linear_rep_geometry
  ☆86Updated last week
• r-three / t-few
  Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
  ☆443Updated last year
• for-ai / parameter-efficient-moe
  ☆251Updated last year
• EleutherAI / delphi
  ☆151Updated this week
• kmeng01 / rome
  Locating and editing factual associations in GPT (NeurIPS 2022)
  ☆604Updated 10 months ago