Alternatives and similar repositories for Mechanistic-Interpretability

Users that are interested in Mechanistic-Interpretability are comparing it to the libraries listed below

• kesimeg / awesome-turkish-language-models
  A curated list of Turkish AI models, datasets, papers
  ☆45Updated last month
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆202Updated 10 months ago
• neelnanda-io / Crosscoders
  ☆54Updated 11 months ago
• malibayram / tokenizer
  Dilbilim kurallarını temel alarak çok dilli metinleri işlemek ve anlam bütünlüğünü korumak için gelişmiş bir tokenizer altyapısı geliştir…
  ☆15Updated 2 months ago
• hkproj / multi-latent-attention
  ☆45Updated 4 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆216Updated last week
• apoorvkh / academic-pretraining
  $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
  ☆147Updated 2 weeks ago
• saprmarks / dictionary_learning
  ☆348Updated last month
• ARBORproject / arborproject.github.io
  ☆81Updated 7 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆374Updated 11 months ago
• jacobdunefsky / transcoder_circuits
  ☆175Updated 11 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 11 months ago
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆330Updated 11 months ago
• safety-research / persona_vectors
  Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  ☆258Updated 2 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆221Updated 10 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆136Updated 3 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆161Updated 5 months ago
• interp-reasoning / thought-anchors
  ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
  ☆86Updated last month
• anthropics / attribution-graphs-frontend
  https://transformer-circuits.pub/2025/attribution-graphs/methods.html
  ☆86Updated 6 months ago
• tim-lawson / mlsae
  Multi-Layer Sparse Autoencoders (ICLR 2025)
  ☆26Updated 8 months ago
• jbloomAus / SAEDashboard
  ☆73Updated last week
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆31Updated last year
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆640Updated this week
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆311Updated 2 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆291Updated 10 months ago
• ayyucedemirbas / Deep-Learning-Tips-and-Tricks
  ☆20Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 5 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆244Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆274Updated last year
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆23Updated last week