391 citations · 1.3k across the 14 of their papers we have counts for
14 papers
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Adly Templeton, Tom Conerly, Jonathan Marcus +23
We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictiona…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
Taedong Yun, Eric Yang, Mustafa Safdari +13
We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…
Specific versus General Principles for Constitutional AI
Sandipan Kundu, Yuntao Bai, Saurav Kadavath +33
Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-pre…
Measuring Faithfulness in Chain-of-Thought Reasoning
Tamera Lanham, Anna Chen, Ansh Radhakrishnan +27
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasonin…
The Capacity for Moral Self-Correction in Large Language Models
Deep Ganguli, Amanda Askell, Nicholas Schiefer +46
We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…
Discovering Language Model Behaviors with Model-Written Evaluations
Ethan Perez, Sam Ringer, Kamilė Lukošiūtė +60
As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (w…
Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48
As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…
Measuring Progress on Scalable Oversight for Large Language Models
Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez +43
Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on m…
Toy Models of Superposition
Nelson Elhage, Tristan Hume, Catherine Olsson +13
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Deep Ganguli, Liane Lovitt, Jackson Kernion +33
We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main…
Language Models (Mostly) Know What They Know
Saurav Kadavath, Tom Conerly, Amanda Askell +33
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models a…
Scaling Laws and Interpretability of Learning from Repeated Data
Danny Hernandez, Tom Brown, Tom Conerly +15
Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or uninte…
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Yuntao Bai, Andy Jones, Kamal Ndousse +28
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment tra…