Christopher Potts

3
Papers
115
Total Citations

Papers (3)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

ICML 2025
100
citations

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

ICLR 2025
14
citations

Blackbox Model Provenance via Palimpsestic Membership Inference

NeurIPS 2025arXiv
1
citations