3 papers
cs.LG2025
Robustly Improving LLM Fairness in Realistic Settings via Interpretability
Adam Karvonen, Samuel Marks
Large language models (LLMs) are increasingly deployed in high-stakes hiring applications, making decisions that directly impact people's careers and livelihoods. While prior studi…
cs.LG2025
Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need
Adam Karvonen
Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model log…
cs.LG2024
Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
Adam Karvonen, Can Rager, Samuel Marks +1
Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE developme…