Alternatives and similar repositories for readingwhatwecan

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

• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆216Updated last week
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆53Updated 3 years ago
• quantified-uncertainty / ai-safety-papers
  ☆22Updated 4 years ago
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆15Updated 2 years ago
• moirage / alignment-research-dataset
  A dataset of alignment research and code to reproduce it
  ☆78Updated 2 years ago
• anthropics / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆202Updated 4 years ago
• collin-burns / discovering_latent_knowledge
  ☆284Updated last year
• callummcdougall / sae_visualizer
  ☆29Updated last year
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆242Updated last year
• anthropics / evals
  ☆328Updated last year
• redwoodresearch / rust_circuit_public
  ☆66Updated 2 years ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆20Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆124Updated last month
• METR / public-tasks
  ☆117Updated last week
• METR / task-standard
  METR Task Standard
  ☆171Updated 11 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆101Updated 2 years ago
• redwoodresearch / remix_public
  ☆20Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆315Updated last year
• jessicarumbelow / Backwards
  ☆85Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆76Updated 2 years ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆150Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• apple / ml-np-rasp
  ☆20Updated 2 years ago
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆74Updated 3 years ago
• aypan17 / machiavelli
  ☆144Updated 6 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆37Updated last year
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆199Updated 2 years ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆238Updated 5 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆133Updated 3 years ago
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆212Updated last year