4 papers
Data Whitening Improves Sparse Autoencoder Learning
Ashwin Saraswatula, David Klindt
Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE tra…
From superposition to sparse codes: interpretable representations in neural networks
David Klindt, Charles O'Neill, Patrik Reizinger +2
Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures,…
Latent computing by biological neural networks: A dynamical systems framework
Fatih Dinc, Marta Blanco-Pozo, David Klindt +8
Although individual neurons and neural populations exhibit the phenomenon of representational drift, perceptual and behavioral outputs of many neural circuits can remain stable acr…
Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
Charles O'Neill, Alim Gumran, David Klindt
A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinea…