Jorge Roldan's picture

Jorge Roldan

roldanjorge

·

AI & ML interests

None yet

Recent Activity

liked a model about 2 months ago

google/gemma-scope-2

upvoted a collection about 2 months ago

Gemma Scope Release

liked a model about 2 months ago

google/gemma-2-9b

View all activity

Organizations

liked a model about 2 months ago

google/gemma-scope-2

Updated Dec 19, 2025 • 70

upvoted a collection about 2 months ago

Gemma Scope Release

A comprehensive, open suite of sparse autoencoders for Gemma 2 2B and 9B. • 10 items • Updated Jul 10, 2025 • 20

liked a model about 2 months ago

google/gemma-2-9b

Text Generation • Updated Aug 7, 2024 • 53.3k • • 690

upvoted a collection about 2 months ago

RM Sycophancy (LLaMa)

https://alignment.anthropic.com/2025/auditing-mo-replication/ • 9 items • Updated 2 days ago • 2

liked a dataset 5 months ago

openai/gdpval

Viewer • Updated 7 days ago • 220 • 32.7k • 461

liked a Space 5 months ago

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

upvoted 2 collections 5 months ago

Llama 2 Family

This collection hosts the transformers and original repos of the Llama 2 and Llama Guard releases • 13 items • Updated Dec 6, 2024 • 95

Meta's Llama2 models

12 items • Updated Dec 13, 2024 • 265

liked a model 5 months ago

meta-llama/Llama-2-7b-chat-hf

Text Generation • Updated Apr 17, 2024 • 419k • 4.71k

upvoted 4 papers 6 months ago

Beyond Transcription: Mechanistic Interpretability in ASR

Paper • 2508.15882 • Published Aug 21, 2025 • 87

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published Aug 21, 2025 • 269

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published Aug 2, 2025 • 238

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Paper • 2508.14041 • Published Aug 19, 2025 • 59

upvoted a collection 6 months ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 135 items • Updated Dec 18, 2025 • 118

upvoted a paper 6 months ago

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Paper • 2408.05147 • Published Aug 9, 2024 • 41

liked a model 6 months ago

google/gemma-scope

Updated Aug 29, 2024 • 192

upvoted a collection 6 months ago

The Well

A 15TB collection of physics simulation datasets. • 18 items • Updated Mar 24, 2025 • 43

liked a Space 8 months ago

Exbert

Explore BERT model's attention mechanisms

updated a collection 8 months ago

foundational

3 items • Updated Jun 21, 2025

liked a model 8 months ago

facebook/bart-large-mnli

Zero-Shot Classification • 0.4B • Updated Sep 5, 2023 • 3.57M • • 1.53k