◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Kaarel Hänni

4 papers hereh-index 450 citations5 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author2

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.AI1

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.AI2024

Cluster-norm for Unsupervised Probing of Knowledge

Walter Laurito, Sharan Maiya, Grégoire Dhimoïla +3

The deployment of language models brings challenges in generating reliable information, especially when these models are fine-tuned using human preferences. To extract encoded know…

cs.LG2024

Mathematical Models of Computation in Superposition

Kaarel Hänni, Jake Mendel, Dmitry Vaintrob +1

Superposition -- when a neural network represents more ``features'' than it has dimensions -- seems to pose a serious challenge to mechanistically interpreting current AI systems.…

cs.LG2024

The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill +7

Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear…

cs.LG2024

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability

Lucius Bushnaq, Jake Mendel, Stefan Heimersheim +5

Mechanistic Interpretability aims to reverse engineer the algorithms implemented by neural networks by studying their weights and activations. An obstacle to reverse engineering ne…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.