Cite
Park, Kiho, et al. The Linear Representation Hypothesis and the Geometry of Large Language Models. arXiv:2311.03658, arXiv, 17 July 2024. arXiv.org, http://arxiv.org/abs/2311.03658.
Metadata
Title: The Linear Representation Hypothesis and the Geometry of Large Language Models Authors: Kiho Park, Yo Joong Choe, Victor Veitch Cite key: park2024
Links
Abstract
Informally, the ‘linear representation hypothesis’ is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does “linear representation” actually mean? And, how do we make sense of geometric notions (e.g., cosine similarity or projection) in the representation space? To answer these, we use the language of counterfactuals to give two formalizations of “linear representation”, one in the output (word) representation space, and one in the input (sentence) space. We then prove these connect to linear probing and model steering, respectively. To make sense of geometric notions, we use the formalization to identify a particular (non-Euclidean) inner product that respects language structure in a sense we make precise. Using this causal inner product, we show how to unify all notions of linear representation. In particular, this allows the construction of probes and steering vectors using counterfactual pairs. Experiments with LLaMA-2 demonstrate the existence of linear representations of concepts, the connection to interpretation and control, and the fundamental role of the choice of inner product.
Notes
From Obsidian
(As notes and annotations from Zotero are one-way synced, this section include a link to another note within Obsidian to host further notes)
The-Linear-Representation-Hypothesis-and-the-Geometry-of-Large-Language-Models
From Zotero
(one-way sync from Zotero)
Annotations
Highlighting colour codes
Link to original
- Note: highlights for quicker reading or comments stemmed from reading the paper but might not be too related to the paper
- External Insight: Insights from other works but was mentioned in the paper
- Question/Critic: questions or comments on the content of paper
- Claim: what the paper claims to have found/achieved
- Finding: new knowledge presented by the paper
- Important: anything interesting enough (findings, insights, ideas, etc.) that’s worth remembering
From Zotero
(one-way sync from Zotero) Imported: 2024-12-08
Note | View in local Zotero: page 2
