Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Aleksandar Makelov Georg Lange Neel Nanda

Published in: CoRR (2024)

Keyphrases

high dimensional
control system
control method
machine learning
sparse representation
rule base
adaptive control
real world
case study
expert systems
hidden markov models
denoising
natural images
handwritten digits
robot control