Alternatives and similar repositories for spd

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

• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆31Updated 4 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆109Updated 3 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆291Updated 10 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆161Updated 5 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆228Updated 2 months ago
• ARBORproject / arborproject.github.io
  ☆81Updated 7 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
• 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
• jbloomAus / SAEDashboard
  ☆73Updated last week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 11 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆75Updated 2 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆128Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆244Updated last year
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆98Updated 2 weeks ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆24Updated 10 months ago
• google-deepmind / mishax
  ☆142Updated last month
• saprmarks / dictionary_learning
  ☆348Updated last month
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆247Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆77Updated 2 weeks ago
• redwoodresearch / Easy-Transformer
  ☆126Updated last year
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆208Updated last week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆77Updated 2 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆192Updated last year
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆640Updated this week
• collin-burns / discovering_latent_knowledge
  ☆278Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 5 months ago
• neelnanda-io / Crosscoders
  ☆54Updated 11 months ago
• curt-tigges / probity
  ☆19Updated 6 months ago