Search Results for author:
Found 4 papers, 2 papers with code
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
We introduce methods for discovering and applying sparse feature circuits.
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs.
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
In this work, we curate high-quality datasets of true/false statements and use them to study in detail the structure of LLM representations of truth, drawing on three lines of evidence: 1.
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
