4 papers · 1 filter
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absor…
Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva +7
The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N:M) pruning is well-established for we…
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is of…
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Andrey Galichin, Alexey Dontsov, Polina Druzhinina +4
Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms b…