Search Results for author:
Found 2 papers, 1 papers with code
A Geometric Notion of Causal Probing
The linear subspace hypothesis (Bolukbasi et al., 2016) states that, in a language model's representation space, all information about a concept such as verbal number is encoded in a linear subspace.
Generalizing Backpropagation for Gradient-Based Interpretability
Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
