arXiv Computation and Language
Calibrating Lightweight Sparse Autoencoder Feature Steering
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 1
Enhancing SAE-based Steering via Neighbor Integrated Feature Selection
arXiv:2608.28806v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) disentangle model activations into interpretable features and are widely used for steering large language models. Most exist...
arXiv Machine Learning
Jun 30
Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
arXiv:2507. 23220v2 Announce Type: replace-cross Abstract: Traditional topic models are effective at uncovering latent themes in large text collections.
arXiv AI
Jun 30
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
arXiv:2606. 30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges.
arXiv Machine Learning
Jun 17
Stable and Steerable Sparse Autoencoders with Weight Regularization
arXiv:2603. 04198v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices.
arXiv Machine Learning
Sep 10
Disentangling Steering Vectors
arXiv:2609.07037v1 Announce Type: new Abstract: Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional...
arXiv Machine Learning
Sep 7
SharedSAE: One Feature Dictionary Across Language Models
SharedSAE demonstrates that a single sparse autoencoder can replace multiple model‑specific SAEs by using a shared dictionary with model‑specific encoder‑decoder pairs. It preserves activation magnitudes, normalizes only selection scores, and supports single‑model inference via model dropout. Trained on four 1B‑scale language models, SharedSAE retains 96.6% of the mean explained variance of dedicated SAEs, shows higher cross‑model latent correlations, and allows efficient adaptation of new models to the shared latent space.