AsaCooperStickland / situational-awareness-evalsLinks
Measuring the situational awareness of language models
☆36Updated last year
Alternatives and similar repositories for situational-awareness-evals
Users that are interested in situational-awareness-evals are comparing it to the libraries listed below
Sorting:
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- A library for efficient patching and automatic circuit discovery.☆70Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 7 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
- Sparse Autoencoder Training Library☆53Updated 2 months ago
- ☆92Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆192Updated last week
- ☆23Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- A quick way to get started with Transformer Lens☆14Updated last year
- ☆87Updated 11 months ago
- Functional Benchmarks and the Reasoning Gap☆88Updated 9 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆56Updated 8 months ago
- A repository for transformer critique learning and generation☆90Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆99Updated 3 weeks ago
- ☆22Updated 9 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆112Updated last year
- ☆121Updated 11 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆206Updated 6 months ago
- ☆101Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- ☆98Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated last week
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆28Updated last year
- ☆137Updated 8 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year