METR / public-tasks

Related projects ⓘ

Alternatives and complementary repositories for public-tasks

• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆63Updated this week
• METR / task-standard
  METR Task Standard
  ☆124Updated 3 weeks ago
• google-deepmind / mishax
  ☆101Updated 3 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆179Updated 4 months ago
• aidanmclaughlin / AidanBench
  Aidan Bench attempts to measure <big_model_smell> in LLMs.
  ☆98Updated this week
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 4 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆200Updated 4 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆44Updated last month
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆48Updated 3 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated last month
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆229Updated 8 months ago
• JD-P / minihf
  MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…
  ☆152Updated this week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆123Updated last month
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆81Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆106Updated last week
• neoneye / ARC-Interactive-History-Dataset
  The history files when recording human interaction while solving ARC tasks
  ☆95Updated this week
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆33Updated 9 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆77Updated last week
• amack315 / unsupervised-steering-vectors
  ☆24Updated 6 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆200Updated 9 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆84Updated this week
• EleutherAI / sae
  Sparse autoencoders
  ☆344Updated last week
• saprmarks / feature-circuits
  ☆105Updated last month
• Aleph-Alpha / scaling
  Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…
  ☆51Updated 3 weeks ago
• teknium1 / LLM-Benchmark-Logs
  Just a bunch of benchmark logs for different LLMs
  ☆115Updated 3 months ago
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆93Updated 3 months ago