133 citations · 281 across the 44 of their papers we have counts for
12 papers · 1 filter
Disentangling Fact from Grid Cell Fiction in Trained Deep Path Integrators
Rylan Schaeffer, Mikail Khona, Sanmi Koyejo +1
Work on deep learning-based models of grid cells suggests that grid cells generically and robustly arise from optimizing networks to path integrate, i.e., track one's spatial posit…
What Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity from Incidental Causes
Victor Lecomte, Kushal Thaman, Rylan Schaeffer +3
Polysemantic neurons -- neurons that activate for a set of unrelated features -- have been seen as a significant obstacle towards interpretability of task-optimized deep networks,…
Testing Assumptions Underlying a Unified Theory for the Origin of Grid Cells
Rylan Schaeffer, Mikail Khona, Adrian Bertagnoli +2
Representing and reasoning about physical space is fundamental to animal survival, and the mammalian lineage expresses a wealth of specialized neural representations that encode sp…
Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells
Rylan Schaeffer, Mikail Khona, Tzuhsuan Ma +3
To solve the spatial problems of mapping, localization and navigation, the mammalian lineage has developed striking spatial representations. One important spatial representation is…
Pretraining on the Test Set Is All You Need
Rylan Schaeffer
Inspired by recent work demonstrating the promise of smaller Transformer-based language models pretrained on carefully curated data, we supercharge such approaches by investing hea…
Deceptive Alignment Monitoring
Andres Carranza, Dhruv Pai, Rylan Schaeffer +2
As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the mo…
Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting
Rylan Schaeffer, Kateryna Pistunova, Samar Khanna +2
Language models can be prompted to reason through problems in a manner that significantly improves performance. However, \textit{why} such prompting improves performance is unclear…
FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation
Dhruv Pai, Andres Carranza, Rylan Schaeffer +2
We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the…
Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data
Brando Miranda, Alycia Lee, Sudharsan Sundar +4
Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an import…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
Are Emergent Abilities of Large Language Models a Mirage?
Rylan Schaeffer, Brando Miranda, Sanmi Koyejo
Recent work claims that large language models display emergent abilities, abilities not present in smaller-scale models that are present in larger-scale models. What makes emergent…
Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Rylan Schaeffer, Mikail Khona, Zachary Robertson +5
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever…