Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Philip Quirke
Observed name:
Quirke, Philip
Institutions:
University of Utah,
University of Delaware
Observed institutions:
University of Utah,
University of Delaware
OpenAlex ID:
A5093876032
Understanding Addition in Transformers
2023
·
Quirke, Philip
, Barez, Fazl
·
arXiv (Cornell University)
·
27
PDF
Planning in a recurrent neural network that plays Sokoban
2024
·
Taufeeque, Mohammad
, Quirke, Philip
, et al.
·
arXiv (Cornell University)
·
19
PDF
Understanding Addition and Subtraction in Transformers
2024
·
Quirke, Philip
, Neo, Clement
, et al.
·
arXiv (Cornell University)
·
13
PDF
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
2026
·
Michael Lan
, Narmeen Fatimah Oozeer
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
3
PDF
The Capability Frontier: Benchmarks Miss 82% of Model Performance
2026
·
Fowler, Bradley
, Smith, Ryan
, et al.
·
arXiv (Cornell University)
·
2
PDF
Necessary, Decodable and Reversible, Yet Not Transferable: A Stress Test for Attention-Head Role Claims
2026
·
Quirke, Philip
·
arXiv (Cornell University)
·
2
PDF
Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering
2026
·
Oozeer, Narmeen
, Raval, Shivam
, et al.
·
arXiv (Cornell University)
·
1
PDF
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models
2025
·
Quirke, Philip
, Oozeer, Narmeen
, et al.
·
arXiv (Cornell University)
·
1
PDF
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
2025
·
Abir Harrasse
, Philip Quirke
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
1
PDF
What Accuracy Hides In Learned Transformer Programs
2026
·
Lee, Jonathan
, Oozeer, Narmeen
, et al.
·
arXiv (Cornell University)
PDF
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
2026
·
Association for Computational Linguistics 2026
, Abdullah, Amir
, et al.
·
Underline Science Inc.
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
2025
·
Association for Computational Linguistics 2025
, Abdullah, Amir
, et al.
·
Underline Science Inc.
Position: Require Frontier AI Labs To Release Small "Analog" Models
2025
·
Shriyash Upadhyay
, Philip Quirke
, et al.
·
neural information processing systems
Show more works
View as search
Works count:
15
Citation count:
71
H-index:
3
I10-index:
3
Year
Topic
Type
