9 citations · 19 across the 7 of their papers we have counts for
8 papers
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd +16
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize t…
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
Zhuonan Yang, Jacob Xiaochen Li, Francisco Piedrahita Velez +5
One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answ…
In-Context Algebra
Eric Todd, Jannik Brinkmann, Rohit Gandikota +1
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their in…
The Dual-Route Model of Induction
Sheridan Feucht, Eric Todd, Byron Wallace +1
Prior work on in-context copying has shown the existence of induction heads, which attend to and promote individual tokens during copying. In this work we discover a new type of in…
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson +26
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
Aaron Mueller, Jannik Brinkmann, Millicent Li +10
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc ev…
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Jaden Fiotto-Kaufman, Alexander R. Loftus, Eric Todd +17
We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is…
Function Vectors in Large Language Models
Eric Todd, Millicent L. Li, Arnab Sen Sharma +3
We report the presence of a simple neural mechanism that represents an input-output function as a vector within autoregressive transformer language models (LMs). Using causal media…