Collection by
Apr 7, 2024
Apr 7, 2024
Collections
Discover the best community collections!
Collections including paper arxiv:2404.03646
Collection by
Apr 7, 2024
Apr 7, 2024
Collection by
Apr 7, 2024
Apr 7, 2024
Collection by
Apr 7, 2024
Apr 7, 2024
Collection by
Apr 7, 2024
Apr 7, 2024
Collection by
May 1, 2024
May 1, 2024
-
Advancing LLM Reasoning Generalists with Preference Trees
Paper • 2404.02078 • Published • 44 -
Locating and Editing Factual Associations in Mamba
Paper • 2404.03646 • Published • 3 -
Locating and Editing Factual Associations in GPT
Paper • 2202.05262 • Published • 1 -
KAN: Kolmogorov-Arnold Networks
Paper • 2404.19756 • Published • 110
Collection by
Apr 8, 2024
Apr 8, 2024
-
JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
Paper • 2310.00535 • Published • 2 -
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Paper • 2211.00593 • Published • 2 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Paper • 2307.09458 • Published • 11
Collection by
Apr 24, 2024
Apr 24, 2024
-
Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
Paper • 2403.07487 • Published • 15 -
LocalMamba: Visual State Space Model with Windowed Selective Scan
Paper • 2403.09338 • Published • 8 -
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
Paper • 2403.14520 • Published • 34 -
SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Paper • 2403.15360 • Published • 12
Collection by
9 days ago
9 days ago
-
Partially Rewriting a Transformer in Natural Language
Paper • 2501.18838 • Published • 2 -
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Paper • 2501.17148 • Published • 1 -
Sparse Autoencoders Trained on the Same Data Learn Different Features
Paper • 2501.16615 • Published • 1 -
Open Problems in Mechanistic Interpretability
Paper • 2501.16496 • Published • 19