arXiv Machine Learning
Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 7
InverseScope: Scalable Activation Inversion for Interpreting Large Language Models
arXiv:2506. 07406v3 Announce Type: replace-cross Abstract: Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research.
arXiv AI
Jul 14
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
arXiv:2607. 10803v1 Announce Type: cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability.
arXiv AI
Jun 26
Discovering Millions of Interpretable Features with Sparse Autoencoders
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 Machine Learning
Jul 16
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
arXiv:2607. 13047v1 Announce Type: new Abstract: Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations.
arXiv Machine Learning
Jul 10
Prompt Compression via Activation Aggregation
arXiv:2607. 08399v1 Announce Type: cross Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response.
arXiv Machine Learning
Jun 4
Transmuting prompts into weights
arXiv:2510. 08734v3 Announce Type: replace Abstract: A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or through updates to their weight matrices.