ApolloResearch / deception-detectionLinks
☆22Updated 8 months ago
Alternatives and similar repositories for deception-detection
Users that are interested in deception-detection are comparing it to the libraries listed below
Sorting:
- ☆23Updated last year
- ☆49Updated 2 years ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 9 months ago
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- ☆37Updated 10 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated 11 months ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆62Updated 4 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated this week
- ☆59Updated 2 years ago
- ☆23Updated 11 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- ☆79Updated 3 weeks ago
- Sparse probing paper full code.☆63Updated last year
- [ICLR 2025] General-purpose activation steering library☆115Updated last month
- ☆108Updated 8 months ago
- ☆22Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆221Updated last week
- ☆130Updated 2 years ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆151Updated 5 months ago
- ☆16Updated last year
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆20Updated 2 years ago
- ☆192Updated 2 weeks ago
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆38Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆42Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆127Updated 8 months ago
- ☆133Updated 2 weeks ago