3

Selective Generalization: Improving Capabilities While Maintaining Alignment
Training to improve capabilities may cause undesired changes in model behavior. For example, training models on oversight protocols or …
Ariana Azarbal, Matthew A. Clarke, Jorio Cocolla, Cailley Factor, Alex Cloud
PDF Code Dataset Project
Selective Generalization: Improving Capabilities While Maintaining Alignment
MAGELLAN: Automated Generation of Interpretable Computational Models for Biological Reasoning
Computational models have become essential tools for understanding signalling networks and their non-linear dynamics. However, these …
Matthew A. Clarke, Charlie George Barker, Yuxin Sun, Theodoros I. Roumeliotis, Jyoti S. Choudhary, Jasmin Fisher
PDF Code Project DOI
MAGELLAN: Automated Generation of Interpretable Computational Models for Biological Reasoning
Predicting Personalised Therapeutic Combinations in Non-Small Cell Lung Cancer Using In Silico Modelling
The disease burden from non-small cell lung cancer (NSCLC) adenocarcinoma is substantial, with around a million new cases diagnosed …
Matthew A. Clarke, Charlie George Barker, Ashley Nicholls, Matt P. Handler, Lisa Pickard, Amna Shah, David Walter, Etienne De Braekeleer, Udai Banerji, Jyoti Choudhary, Saif Ahmed, Ultan McDermott, Gregory J. Hannon, Jasmin Fisher
PDF Project
Predicting Personalised Therapeutic Combinations in Non-Small Cell Lung Cancer Using In Silico Modelling
Compositionality and Ambiguity: Latent Co-occurrence and Interpretable Subspaces
Sparse AutoEncoder (SAE) latents show promise as a method for extracting interpretable features from large language models (LM), but …
Matthew A. Clarke, Hardik Bhatnagar, Joseph Bloom
PDF Code Dataset Project Video
Compositionality and Ambiguity: Latent Co-occurrence and Interpretable Subspaces