☆284Mar 2, 2024Updated 2 years ago
Alternatives and similar repositories for discovering_latent_knowledge
Users that are interested in discovering_latent_knowledge are comparing it to the libraries listed below
Sorting:
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Mar 2, 2026Updated last week
- Tools for understanding how transformer predictions are built layer-by-layer☆570Aug 7, 2025Updated 7 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆572Jan 28, 2025Updated last year
- Erasing concepts from neural representations with provable guarantees☆243Jan 27, 2025Updated last year
- ☆58Jun 30, 2023Updated 2 years ago
- ☆118Feb 11, 2025Updated last year
- Utilities for the HuggingFace transformers library☆75Jan 21, 2023Updated 3 years ago
- A library for mechanistic interpretability of GPT-style language models☆3,133Updated this week
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Jun 19, 2024Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆957Aug 14, 2024Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆134Mar 9, 2024Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 4 months ago
- ☆60Mar 9, 2023Updated 3 years ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆19Dec 14, 2024Updated last year
- Locating and editing factual associations in GPT (NeurIPS 2022)☆734Apr 20, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆248Feb 27, 2026Updated last week
- ☆12Oct 23, 2022Updated 3 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆292Jul 20, 2024Updated last year
- ☆552Feb 5, 2024Updated 2 years ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆127Mar 22, 2024Updated last year
- Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts☆16Feb 26, 2024Updated 2 years ago
- ☆333Jul 2, 2024Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆213May 23, 2024Updated last year
- PAIR.withgoogle.com and friend's work on interpretability methods☆222Feb 4, 2026Updated last month
- ☆1,074Mar 6, 2024Updated 2 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Sep 13, 2020Updated 5 years ago
- ☆38Oct 3, 2023Updated 2 years ago
- ☆68May 18, 2023Updated 2 years ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Jun 13, 2024Updated last year
- ☆96Oct 27, 2022Updated 3 years ago
- ☆576Jul 19, 2024Updated last year
- Code release for "TempLM: Distilling Language Models into Template-Based Generators"☆14Jul 21, 2022Updated 3 years ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆16Feb 24, 2026Updated last week
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28May 23, 2024Updated last year
- Code repo for the model organisms and convergent directions of EM papers.☆53Sep 22, 2025Updated 5 months ago
- [ICLR 2023] PyTorch code of Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees☆24Jun 19, 2023Updated 2 years ago
- PyTorch-based library for various kinds of representational-similarity analysis☆24Jun 7, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆297Nov 10, 2023Updated 2 years ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,739Nov 15, 2025Updated 3 months ago