16 citations · 18 across the 13 of their papers we have counts for
5 papers · 1 filter
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Daniel Wurgaft, Can Rager, Matthew Kowal +13
Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space…
Priors in Time: Missing Inductive Biases for Language Model Interpretability
Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur +13
Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are ind…
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
Eric Bigelow, Daniel Wurgaft, YingQiao Wang +4
Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been…
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando +39
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories…
Mechanistic Mode Connectivity
Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick +2
We study neural network loss landscapes through the lens of mode connectivity, the observation that minimizers of neural networks retrieved via training on a dataset are connected…