Gabriele Sarti's picture

Gabriele Sarti

gsarti

·

https://gsarti.com

AI & ML interests

Interpretability for generative language models

Recent Activity

updated a collection 4 days ago

🔍 Daily Picks in Interpretability & Analysis of LMs

upvoted a paper 4 days ago

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

updated a collection 6 days ago

🔍 Daily Picks in Interpretability & Analysis of LMs

View all activity

Organizations

gsarti's activity

upvoted a paper 4 days ago

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

Paper • 2412.16247 • Published 18 days ago • 1

upvoted a paper 6 days ago

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs

Paper • 2410.11179 • Published Oct 15, 2024 • 1

upvoted a paper 17 days ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published 18 days ago • 337

upvoted 2 papers 18 days ago

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models

Paper • 2412.05353 • Published Dec 6, 2024 • 1

The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units

Paper • 2411.02280 • Published Nov 4, 2024 • 1

upvoted a paper 21 days ago

Inferring Functionality of Attention Heads from their Parameters

Paper • 2412.11965 • Published 21 days ago • 2

upvoted a paper 24 days ago

LatentQA: Teaching LLMs to Decode Activations Into Natural Language

Paper • 2412.08686 • Published 26 days ago • 1

upvoted a paper 27 days ago

Training Large Language Models to Reason in a Continuous Latent Space

Paper • 2412.06769 • Published 28 days ago • 68

upvoted an article about 1 month ago

Article

EuroLLM-9B

By

•

Dec 2, 2024

• 105

upvoted 2 collections about 1 month ago

NLI Eval Datasets

A curated collection of NLI evaluation datasets. Each dataset is exactly as originally proposed • 19 items • Updated Nov 12, 2024 • 3

🇮🇹👓 LLaVA-NDiNO

HF Collection for the models of the paper "LLaVA-NDiNO: Empowering LLMs with Multimodality for the Italian Language" • 7 items • Updated Oct 20, 2024 • 3

upvoted a paper about 1 month ago

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Paper • 2411.17465 • Published Nov 26, 2024 • 77

upvoted a collection about 1 month ago

SmolVLM

State-of-the-art compact VLMs for on-device applications: Base, Synthetic, and Instruct • 5 items • Updated 15 days ago • 30

upvoted an article about 1 month ago

Article

Halo: Open Source Health Tracking with Wearables

By

•

Nov 19, 2024

• 99

upvoted 5 papers about 2 months ago

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Paper • 2411.14257 • Published Nov 21, 2024 • 9

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Paper • 2411.12580 • Published Nov 19, 2024 • 2

Controllable Context Sensitivity and the Knob Behind It

Paper • 2411.07404 • Published Nov 11, 2024 • 1

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

Paper • 2411.10397 • Published Nov 15, 2024 • 1

Counterfactual Generation from Language Models

Paper • 2411.07180 • Published Nov 11, 2024 • 5

upvoted a collection 2 months ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 15 days ago • 197