Gabriele Sarti's picture

Gabriele Sarti

gsarti

·

https://gsarti.com

AI & ML interests

Interpretability for generative language models

Recent Activity

updated a Space 2 days ago

gsarti/it5-demo

upvoted a paper 3 days ago

ReAct: Synergizing Reasoning and Acting in Language Models

liked a model 3 days ago

lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual

View all activity

Organizations

gsarti's activity

updated a Space 2 days ago

IT5 Demo

Test fine-tuned IT5 models for Italian language generation

upvoted a paper 3 days ago

ReAct: Synergizing Reasoning and Acting in Language Models

Paper • 2210.03629 • Published Oct 6, 2022 • 17

liked a model 3 days ago

lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual

Updated 10 days ago • 417 • 15

upvoted a collection 3 days ago

Reasoning Datasets

Distilled synthetic Reasoning datasets • 7 items • Updated 7 days ago • 48

updated a collection 3 days ago

🇮🇹 Italian NLP Resources

Collection of models, datasets and demos relevant to Italian NLP 🇮🇹 • 282 items • Updated 3 days ago • 24

upvoted an article 5 days ago

Article

Open-source DeepResearch – Freeing our search agents

6 days ago

• 828

updated a collection 5 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97

upvoted a paper 5 days ago

Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution

Paper • 2501.18887 • Published 10 days ago • 1

updated a collection 5 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97

upvoted a paper 5 days ago

Propositional Interpretability in Artificial Intelligence

Paper • 2501.15740 • Published 14 days ago • 1

upvoted an article 6 days ago

Article

Open-R1: Update #1

By

and 7 others •

8 days ago

• 259

updated a collection 7 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97

upvoted a paper 7 days ago

Partially Rewriting a Transformer in Natural Language

Paper • 2501.18838 • Published 10 days ago • 1

updated a collection 7 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97

upvoted a paper 7 days ago

Sparse Autoencoders Trained on the Same Data Learn Different Features

Paper • 2501.16615 • Published 13 days ago • 1

updated a collection 7 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97

upvoted a paper 7 days ago

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Paper • 2501.17148 • Published 12 days ago • 1

updated a collection 11 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 101 items • Updated 5 days ago • 97