arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.
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:2606. 11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior.
arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.
The paper revisits parsimoniously activated dictionary learning (PADL), a method that imposes a global regularization on the number of activated dictionary atoms. It shows that PADL can be reformulated as a maximum a posteriori estimation under a structured generative model, enabling derivation of generalization guarantees and an analytical tradeoff between sparsity, storage cost, and reconstruction accuracy. Leveraging this insight, the authors propose an efficient PADL algorithm that removes manual hyperparameter tuning, improves reconstruction performance on visual benchmarks, and accelerates inference for vision‑language models.
The paper introduces Consistent Sparse Dictionary Learning (ConSDL), a method that replaces the linear encoder in sparse autoencoders with per‑sample sparse coding to improve dictionary learning. Synthetic experiments show ConSDL achieves near‑perfect recovery of dictionaries and coefficients, and in real vision and language tasks it boosts cross‑seed consistency by 17.6% for dictionaries and 35.9% for coefficients compared to six SAE baselines.
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:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
The paper introduces SAERL, a method that uses Sparse Autoencoders (SAEs) to guide reinforcement learning data engineering for large language models. By mapping training samples into a feature space of interpretable SAE activations, SAERL selects samples with strong, non‑redundant gradient signals, organizes functional regions from easy to hard, and batches from single activation clusters with moderate mixing. Experiments on mathematical reasoning tasks show consistent performance gains across model scales and RL algorithms, with notable improvements on Qwen2.5-Math-1.5B.
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.
The paper argues that the linear representation hypothesis—where neural activations encode concepts as linear mixtures—breaks down under superposition, causing linear decision boundaries to lose linearity after projection. Classical sparse coding with per‑sample inference can recover latent factors, but sparse autoencoders (SAEs) amortise this inference into a fixed encoder, creating a systematic gap that persists across training sizes, latent dimensions, and sparsity levels. Experiments show that the failure of SAEs under out‑of‑distribution compositional shifts stems from poor dictionary learning rather than inference, and that a good dictionary can solve the problem at all tested scales, highlighting scalable dictionary learning as the key open challenge.
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...