research
∙
07/28/2023
The Hydra Effect: Emergent Self-repair in Language Model Computations
We investigate the internal structure of language model computations usi...
share
research
∙
07/18/2023
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Circuit analysis is a promising technique for understanding the internal...
research
∙
01/12/2023
Tracr: Compiled Transformers as a Laboratory for Interpretability
Interpretability research aims to build tools for understanding machine ...
research
∙
03/21/2022
Teaching language models to support answers with verified quotes
Recent large language models often answer factual questions correctly. B...
research
∙
03/26/2021
Alignment of Language Agents
For artificial intelligence to be beneficial to humans the behaviour of ...
research
∙
03/05/2021
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increa...
research
∙
10/23/2020
Algorithms for Causal Reasoning in Probability Trees
Probability trees are one of the simplest models of causal generative pr...
research
∙
10/21/2020
Meta-trained agents implement Bayes-optimal agents
Memory-based meta-learning is a powerful technique to build agents that ...
research
∙
09/25/2019
Neural networks are a priori biased towards Boolean functions with low entropy
Understanding the inductive bias of neural networks is critical to expla...
research
∙
06/05/2019