NeurIPS 2024 Workshop InterpretableAI Submissions

A Theory of Interpretable Approximations
Marco Bressan, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Positional Information Can Emerge Through Causal Attention Making Nearby Token Embeddings Similar Even Without Positional Encodings
Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
The Price of Freedom: An Adversarial Attack on Interpretability Evaluation
Kristoffer Knutsen Wickstrøm, Marina MC Höhne, Anna Hedström
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Can sparse autoencoders be used to decompose and interpret steering vectors?
Harry Mayne, Yushi Yang, Adam Mahdi
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Your Theory Is Wrong: Using Linguistic Frameworks for LLM Probing
Victoria Firsanova
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Riemann Sum Optimization for Accurate Integrated Gradients Computation
Shree Singhi, Swadesh Swain
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
ConceptDrift: Uncovering Biases through the Lens of Foundation Models
Cristian Daniel Paduraru, Antonio Barbalau, Radu Filipescu, Andrei Liviu Nicolicioiu, Elena Burceanu
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Position: In Defence of Post-hoc Explainability
Nick Oh
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
Hugues Turbe, Mina Bjelogrlic, Gianmarco Mengaldo, Christian Lovis
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Residual Stream Analysis with Multi-Layer SAEs
Tim Lawson, Lucy Farnik, Conor Houghton, Laurence Aitchison
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Subgroup Discovery with the Cox Model
Zachary Izzo, Iain Melvin
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Measuring the Reliability of Causal Probing Methods: Tradeoffs, Limitations, and the Plight of Nullifying Interventions
Marc Canby, Adam Davies, Chirag Rastogi, Julia Hockenmaier
- Published: 10 Oct 2024, Last Modified: 06 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations
Kola Ayonrinde, Michael T Pearce
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation
Pedro Alejandro Dal Bianco, Oscar Agustín Stanchi, Facundo Manuel Quiroga, Franco Ronchetti, Enzo Ferrante
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Competence-Based Analysis of Language Models
Adam Davies, Jize Jiang, ChengXiang Zhai
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Aligning Characteristic Descriptors with Images for Human-Expert-like Explainability
Bharat Chandra Yalavarthi, Nalini K. Ratha
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
On Interpretability and Overreliance
Julian Skirzynski, Elena Glassman, Berk Ustun
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Policy-shaped prediction: improving world modeling through interpretability
Miles Richard Hutson, Isaac Kauvar, Nick Haber
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Isometry pursuit
Samson J Koelle, Marina Meila
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Konstantin Donhauser, Gemma Elyse Moran, Aditya Ravuri, Kian Kenyon-Dean, Kristina Ulicna, Cian Eastwood, Jason Hartford
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
You can remove GPT2's LayerNorm by fine-tuning
Stefan Heimersheim
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Explainable Concept Generation through Vision-Language Preference Learning
Aditya Taparia, Som Sagar, Ransalu Senanayake
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
CoS: Enhancing Personalization and Mitigating Bias with Context Steering
Sashrika Pandey, Jerry Zhi-Yang He, Mariah L Schrum, Anca Dragan
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Disentangling Mean Embeddings for Better Diagnostics of Image Generators
Sebastian Gregor Gruber, Pascal Tobias Ziegler, Florian Buettner
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Probable-class Nearest-neighbor Explanations Improve AI & Human Accuracy
Giang Nguyen, Valerie Chen, Mohammad Reza Taesiri, Anh Totti Nguyen
- Published: 10 Oct 2024, Last Modified: 03 Dec 2024
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone