3 citations · 5 across the 9 of their papers we have counts for
4 papers · 1 filter
Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
Constantin Venhoff, Ashkan Khakzar, Sonia Joseph +2
Training vision language models (VLMs) aims to align visual representations from a vision encoder with the textual representations of a pretrained large language model (LLM). Howev…
RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar +1
Activation patching is a standard method in mechanistic interpretability for localizing the components of a model responsible for specific behaviors, but it is computationally expe…
Mixture of Experts Made Intrinsically Interpretable
Xingyi Yang, Constantin Venhoff, Ashkan Khakzar +4
Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on pos…
Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
Michael Lan, Philip Torr, Austin Meek +3
The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence…