arXiv (All)
open access
Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space
Activation space and parameter space provide complementary views of model computation. Activations represent information, while weights read, transform, and write that information. Yet existing interpretability methods largely study the two spaces separately, leaving the connection between represent
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Quantifying Stabilization: A Minimal Information-Theoretic Framework for Representation Robustness under Transformations#104937
- Readers' affect: predicting and understanding readers' emotions with deep learning.#489655
- Stabilization as an Empirical Constraint on Representation: A Minimal Falsification Framework in Machine Learning and Cognitive Systems#77137
- How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations#1141558
- Transfer Calibrated Prediction Powered Inference#1119229
Record · ID 1142043
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive