3 citations · 3 across the 9 of their papers we have counts for
4 papers · 1 filter
Finding Manifolds With Bilinear Autoencoders
Thomas Dooms, Ward Gauderis
Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolat…
Parameterized Synthetic Text Generation with SimpleStories
Lennart Finke, Chandan Sreedhara, Thomas Dooms +6
We present SimpleStories, a large synthetic story dataset in simple language, consisting of 2 million samples each in English and Japanese. Through parameterizing prompts at multip…
Compositionality Unlocks Deep Interpretable Models
Thomas Dooms, Ward Gauderis, Geraint A. Wiggins +1
We propose -net, an intrinsically interpretable architecture combining the compositional multilinear structure of tensor networks with the expressivity and efficiency of deep ne…
Tokenized SAEs: Disentangling SAE Reconstructions
Thomas Dooms, Daniel Wilhelm
Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computation…