Disentangling Neuron Representations with Concept Vectors
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SJYFLK7Urecord.jsonopen to challenge →
read the original abstract
Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated features, makes interpreting individual neurons challenging. This has led to the search for meaningful vectors, known as concept vectors, in activation space instead of individual neurons. The main contribution of this paper is a method to disentangle polysemantic neurons into concept vectors encapsulating distinct features. Our method can search for fine-grained concepts according to the user's desired level of concept separation. The analysis shows that polysemantic neurons can be disentangled into directions consisting of linear combinations of neurons. Our evaluations show that the concept vectors found encode coherent, human-understandable features.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.