arXiv AI
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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 AI
Jun 3
How Quantization Changes Interpretable Features: A Sparse Autoencoder Analysis of Language Models
arXiv:2606. 03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original.
arXiv Computation and Language
Sep 22
Calibrating Lightweight Sparse Autoencoder Feature Steering
arXiv:2506.12576v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fa...
arXiv AI
Jun 16
Rational Sparse Autoencoder
arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.
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 AI
Jun 9
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.