Alternatives and similar repositories for w2s

Users that are interested in w2s are comparing it to the libraries listed below

• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆77Updated 5 months ago
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆160Updated 2 months ago
• davidbau / baukit
  ☆226Updated last year
• roeehendel / icl_task_vectors
  ☆96Updated last year
• ruiqi-zhong / nlparam
  Augmenting Statistical Models with Natural Language Parameters
  ☆27Updated 11 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆60Updated last year
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆74Updated 11 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆99Updated last week
• dtsip / in-context-learning
  ☆238Updated last year
• mega002 / ff-layers
  The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…
  ☆95Updated 4 years ago
• deeplearning-wisc / args
  ☆44Updated last year
• MadryLab / trak
  A fast, effective data attribution method for neural networks in PyTorch
  ☆217Updated 9 months ago
• KihoPark / linear_rep_geometry
  ☆106Updated 6 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆124Updated last year
• PAIR-code / pretraining-tda
  ☆25Updated 6 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• TRAIS-Lab / dattri
  `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
  ☆84Updated 2 months ago
• abhishekpanigrahi1996 / Skill-Localization-by-grafting
  ☆51Updated last year
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆41Updated 6 months ago
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆12Updated 7 months ago
• aviclu / ffn-values
  ☆65Updated 2 years ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆53Updated 11 months ago
• milesaturpin / cot-unfaithfulness
  ☆47Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆178Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• jacobdunefsky / transcoder_circuits
  ☆165Updated 9 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆265Updated last year
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆132Updated 9 months ago
• mmatena / model_merging
  ☆73Updated 3 years ago