2 citations · 2 across the 2 of their papers we have counts for
2 papers
cs.LG2025
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
Maximilian Dreyer, Lorenz Hufe, Jim Berend +3
Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. Whil…
cs.CV2024★ 2 cited
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben +2
The field of mechanistic interpretability aims to study the role of individual neurons in Deep Neural Networks. Single neurons, however, have the capability to act polysemantically…