4 citations · 4 across the 13 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
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…
cs.LG2024
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Adam Karvonen, Benjamin Wright, Can Rager +6
What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representati…
cs.LG2024★ 4 cited
Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
Adam Karvonen
Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface lev…