Relational Composition in Neural Networks: A Survey and Call to Action

19 July 2024

Papers citing "Relational Composition in Neural Networks: A Survey and Call to Action"

7 / 7 papers shown

Title
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment Harrish Thasarathan Julian Forsyth Thomas Fel M. Kowal Konstantinos G. Derpanis 111 7 0 06 Feb 2025
Towards Unifying Interpretability and Control: Evaluation via Intervention Usha Bhalla Suraj Srinivas Asma Ghandeharioun Himabindu Lakkaraju 40 5 0 07 Nov 2024
Residual Stream Analysis with Multi-Layer SAEs Tim Lawson Lucy Farnik Conor Houghton Laurence Aitchison 26 3 0 06 Sep 2024
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models Jack Merullo Carsten Eickhoff Ellie Pavlick 58 13 0 13 Jun 2024
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets Samuel Marks Max Tegmark HILM 102 169 0 10 Oct 2023
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 125 318 0 21 Sep 2022
Compositionality as Lexical Symmetry Ekin Akyürek Jacob Andreas CoGe 50 8 0 30 Jan 2022