Alternatives and similar repositories for universal-neurons

Users that are interested in universal-neurons are comparing it to the libraries listed below

• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 5 months ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 8 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆80Updated 10 months ago
• berlino / seq_icl
  ☆53Updated last year
• mcleish7 / gemstone-scaling-laws
  Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)
  ☆29Updated last week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆77Updated 2 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆63Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆215Updated this week
• KihoPark / linear_rep_geometry
  ☆106Updated 7 months ago
• callummcdougall / sae-exercises-mats
  ☆23Updated last year
• katiekang1998 / reasoning_generalization
  ☆33Updated 8 months ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆30Updated 3 months ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆19Updated 8 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆134Updated 3 months ago
• ckkissane / sae-transfer
  Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"
  ☆12Updated last year
• redwoodresearch / Easy-Transformer
  ☆123Updated last year
• RobertCsordas / moeut
  ☆85Updated last year
• jbloomAus / SAEDashboard
  ☆71Updated last month
• saprmarks / geometry-of-truth
  ☆91Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆84Updated 11 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆41Updated last year
• formll / resolving-scaling-law-discrepancies
  ☆20Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆24Updated 9 months ago
• noanabeshima / matryoshka-saes
  ☆23Updated 10 months ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated last year
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆193Updated last year
• ahans30 / goldfish-loss
  [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
  ☆92Updated 10 months ago
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆15Updated 2 weeks ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆100Updated last year