2 citations · 7 across the 7 of their papers we have counts for
7 papers
Probing for Representation Manifolds in Superposition
Alexander Modell
This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear regression probes by learning…
The Origins of Representation Manifolds in Large Language Models
Alexander Modell, Patrick Rubin-Delanchy, Nick Whiteley
There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key el…
Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks
Alexander Modell, Ian Gallagher, Emma Ceccherini +2
We present a new representation learning framework, Intensity Profile Projection, for continuous-time dynamic network data. Given triples , each representing a time-stampe…
Hierarchical clustering with dot products recovers hidden tree structure
Annie Gray, Alexander Modell, Patrick Rubin-Delanchy +1
In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant o…
Implications of sparsity and high triangle density for graph representation learning
Hannah Sansford, Alexander Modell, Nick Whiteley +1
Recent work has shown that sparse graphs containing many triangles cannot be reproduced using a finite-dimensional representation of the nodes, in which link probabilities are inne…
Spectral embedding and the latent geometry of multipartite networks
Alexander Modell, Ian Gallagher, Joshua Cape +1
Spectral embedding finds vector representations of the nodes of a network, based on the eigenvectors of a properly constructed matrix, and has found applications throughout science…
Spectral clustering under degree heterogeneity: a case for the random walk Laplacian
Alexander Modell, Patrick Rubin-Delanchy
This paper shows that graph spectral embedding using the random walk Laplacian produces vector representations which are completely corrected for node degree. Under a generalised r…