Alternatives and similar repositories for NeuroSurgeon

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

• KihoPark / linear_rep_geometry
  ☆108Updated 8 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆56Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆78Updated 3 months ago
• milesaturpin / cot-unfaithfulness
  ☆49Updated 2 years ago
• MadryLab / trak
  A fast, effective data attribution method for neural networks in PyTorch
  ☆220Updated 11 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 9 months ago
• shauli-ravfogel / rlace-icml
  ☆36Updated 3 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆130Updated 2 years ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆62Updated last year
• roeehendel / icl_task_vectors
  ☆98Updated 2 years ago
• mega002 / ff-layers
  The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…
  ☆97Updated 4 years ago
• redwoodresearch / Easy-Transformer
  ☆127Updated last year
• adamkarvonen / SAEBench
  ☆133Updated last week
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆42Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆248Updated last year
• aviclu / ffn-values
  ☆67Updated 2 years ago
• google-research / jax-influence
  ☆62Updated 3 years ago
• jkallini / mission-impossible-language-models
  Code repository for the paper "Mission: Impossible Language Models."
  ☆54Updated last month
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆166Updated 4 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆114Updated last month
• ARBORproject / arborproject.github.io
  ☆81Updated 8 months ago
• saprmarks / feature-circuits
  ☆191Updated 2 weeks ago
• PAIR-code / pretraining-tda
  ☆29Updated 8 months ago
• davidbau / baukit
  ☆236Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆83Updated 7 months ago
• adamkarvonen / dictionary_learning_demo
  ☆18Updated 2 months ago
• noanabeshima / matryoshka-saes
  ☆23Updated 11 months ago
• nouhadziri / faith-and-fate
  ☆37Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 6 months ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆31Updated 4 months ago