Gabriele Sarti's picture

Gabriele Sarti PRO

gsarti

·

https://gsarti.com

AI & ML interests

Interpretability for generative language models

Recent Activity

liked a model about 1 hour ago

mntss/skip-transcoder-Llama-3.2-1B-131k-nobos

liked a model about 1 hour ago

google/gemma-scope-2b-pt-transcoders

updated a collection about 9 hours ago

🧩 Word games

View all activity

Organizations

gsarti's activity

New activity in gsarti/unsup_wqe_metrics 2 days ago

Update README.md

#3 opened 2 days ago by

New activity in gsarti/unsup_wqe_metrics 3 days ago

Update task category

#2 opened 3 days ago by

Add dataset card, link to paper, and link to code

#1 opened 3 days ago by

commented a paper 7 days ago

Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement

Paper • 2505.23183 • Published 8 days ago • 2 •

commented a paper 14 days ago

Steering Large Language Models for Machine Translation Personalization

Paper • 2505.16612 • Published 15 days ago • 6 •

New activity in gsarti/qe4pe about 1 month ago

[bot] Conversion to Parquet

#1 opened 8 months ago by

parquet-converter

New activity in gsarti/qe4pe 3 months ago

Link paper to HF papers URL

#3 opened 3 months ago by

commented a paper 3 months ago

QE4PE: Word-level Quality Estimation for Human Post-Editing

Paper • 2503.03044 • Published Mar 4 • 6 •

commented a paper 4 months ago

We Can't Understand AI Using our Existing Vocabulary

Paper • 2502.07586 • Published Feb 11 • 10 •

commented a paper 5 months ago

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Paper • 2501.08319 • Published Jan 14 • 11 •

commented a paper 7 months ago

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

Paper • 2411.14257 • Published Nov 21, 2024 • 13 •

New activity in gsarti/opus-mt-tc-en-pl 8 months ago

how to fine tune this model to get better polish translation

#3 opened about 2 years ago by

commented 2 papers 10 months ago

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Paper • 2408.00113 • Published Jul 31, 2024 • 8 •

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Paper • 2408.00584 • Published Aug 1, 2024 • 7 •

New activity in huggingface/HuggingDiscussions 10 months ago

[FEEDBACK] Collections

#12 opened almost 2 years ago by

commented 3 papers 11 months ago

LLM Circuit Analyses Are Consistent Across Training and Scale

Paper • 2407.10827 • Published Jul 15, 2024 • 5 •

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6 •

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6 •

commented 2 papers 12 months ago

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Paper • 2406.17563 • Published Jun 25, 2024 • 4 •

Confidence Regulation Neurons in Language Models

Paper • 2406.16254 • Published Jun 24, 2024 • 10 •