5 papers
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders
Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky +3
Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training r…
Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov +6
The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream…
Teach Old SAEs New Domain Tricks with Boosting
Nikita Koriagin, Yaroslav Aksenov, Daniil Laptev +3
Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features n…
Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
Nikita Balagansky, Yaroslav Aksenov, Daniil Laptev +4
Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via spa…
You Do Not Fully Utilize Transformer's Representation Capacity
Gleb Gerasimov, Yaroslav Aksenov, Nikita Balagansky +2
In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the…