arXiv:2602. 14687v2 Announce Type: replace-cross Abstract: Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
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. 16560v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts.
arXiv:2506. 07691v2 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability.
arXiv:2605. 18629v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional 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.
SyntheticHLS is a framework that uses large language models to create large-scale, diverse synthetic high‑level synthesis (HLS) datasets. It employs an iterative, feedback‑guided mutation loop that transforms seed designs into more complex, scalable ones, guided by quantitative metrics of design complexity and scalability. The resulting datasets outperform manually curated or zero‑shot generated ones in training deep learning models for HLS quality‑of‑results, offering broader coverage of design space and better generalization.