Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Adam Karvonen
Observed name:
Karvonen, Adam
Institutions:
Harvard University,
Carnegie Mellon University
Observed institutions:
Harvard University,
Carnegie Mellon University
OpenAlex ID:
A5109695738
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
2025
·
Karvonen, Adam
, Rager, Can
, et al.
·
arXiv (Cornell University)
·
192
PDF
Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
2024
·
Karvonen, Adam
·
arXiv (Cornell University)
·
70
PDF
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
2024
·
Adam Karvonen
, Benjamin Wright
, et al.
·
neural information processing systems
·
67
PDF
Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
2025
·
Casademunt, Helena
, Juang, Caden
, et al.
·
arXiv (Cornell University)
·
41
PDF
Robustly Improving LLM Fairness in Realistic Settings via Interpretability
2025
·
Karvonen, Adam
, Marks, Samuel
·
arXiv (Cornell University)
·
33
PDF
Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
2024
·
Karvonen, Adam
, Rager, Can
, et al.
·
arXiv (Cornell University)
·
19
PDF
Negation Neglect: When models fail to learn negations in training
2026
·
Mayne, Harry
, McKinney, Lev
, et al.
·
arXiv (Cornell University)
·
10
PDF
Verifying LLM Inference to Detect Model Weight Exfiltration
2025
·
Rinberg, Roy
, Karvonen, Adam
, et al.
·
arXiv (Cornell University)
·
10
PDF
Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need
2025
·
Karvonen, Adam
·
arXiv (Cornell University)
·
8
PDF
Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments
2026
·
Karvonen, Adam
, Ong, Euan
, et al.
·
arXiv (Cornell University)
·
7
PDF
Building Better Activation Oracles
2026
·
Bauer, Jan
, De Schamphelaere, Celeste
, et al.
·
arXiv (Cornell University)
·
6
PDF
Automatically Finding Rule-Based Neurons in OthelloGPT
2025
·
Singh, Aditya
, Wen, Zihang
, et al.
·
arXiv (Cornell University)
PDF
Leveraging Manifold Learning and Relationship Equity Management for Symbiotic Explainable Artificial Intelligence
2023
·
Eric Davis
, Sourya Dey
, et al.
·
AHFE international
Show more works
View as search
Works count:
16
Citation count:
635
H-index:
9
I10-index:
9
Year
Topic
Type