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:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
arXiv:2607. 20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams.
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
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.
Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.
arXiv:2602. 14687v2 Announce Type: replace-cross Abstract: Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations.
arXiv:2606. 14040v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are typically trained to reconstruct the \textbf{entire} residual stream through a sparse dictionary, implicitly assuming that all activation content is amenable to sparse, monosemantic decomposition.
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
arXiv:2606. 27321v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a leading tool for interpreting the representations of vision foundation models, decomposing their polysemantic activations into a larger set of sparse, more monosemantic features.
arXiv:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
arXiv:2609.16229v1 Announce Type: new Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify...
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.