Work

Towards More Interpretable AI With Sparse Autoencoders

Year: 2025

Type: dissertation

Source: DSpace@MIT (Massachusetts Institute of Technology)

Author: Engels, Joshua

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W7112037691

Cites:

Cited by:

Related to: 10