Alternatives and similar repositories for POWERplay:

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

• aogara-ds / hoodwinked-website
  A text-based game where language models learn to lie and to detect lies.
  ☆12Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• UlisseMini / procgen-tools
  Tools for running experiments on RL agents in procgen environments
  ☆18Updated last year
• redwoodresearch / alignment_faking_public
  ☆49Updated 3 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 4 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated 11 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆13Updated 4 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆219Updated 6 months ago
• redwoodresearch / rust_circuit_public
  ☆62Updated 2 years ago
• redwoodresearch / Easy-Transformer
  ☆114Updated 8 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 7 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 10 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆111Updated 10 months ago
• thestephencasper / latent_adversarial_training
  ☆21Updated 9 months ago
• ejones313 / auditing-llms
  ☆54Updated 2 years ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 11 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• anthropics / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆187Updated 3 years ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆144Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆63Updated this week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆102Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆62Updated 2 years ago
• milesaturpin / cot-unfaithfulness
  ☆42Updated last year
• aypan17 / machiavelli
  ☆133Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆178Updated 5 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆199Updated last week
• saprmarks / feature-circuits
  ☆161Updated 2 weeks ago
• siyan-zhao / ICL_decision_boundary
  official code for paper Probing the Decision Boundaries of In-context Learning in Large Language Models. https://arxiv.org/abs/2406.11233…
  ☆17Updated 7 months ago
• nouhadziri / faith-and-fate
  ☆33Updated last year