arXiv (All)
open access
SharedSAE: One Feature Dictionary Across Language Models
Sparse autoencoders (SAEs) are widely used to interpret language model activations, but SAE training and latent labelling are typically repeated for every model. Here, we show that a single shared SAE can replace a collection of dedicated per-model SAEs. Our method, SharedSAE, combines a shared dict
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
- Test-Time Unlearning via Sparse Autoencoder#1110603
- Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects#793793
- Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects#789788
- The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning#974340
- Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA#927561
Record · ID 927640
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