Saes Gemma Scope Open Sparse Autoencoders For Language Model Interpretability

Media Summary: This has been my favorite video so far to make! I think Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ... I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying

Saes Gemma Scope Open Sparse Autoencoders For Language Model Interpretability - Detailed Analysis & Overview

This has been my favorite video so far to make! I think Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ... I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying

Photo Gallery

SAEs | Gemma Scope: Open Sparse Autoencoders for Language Model Interpretability

Demo: Gemma Scope: Sparse autoencoders on Gemma 2

Gemma Scope demo with Neuronpedia

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

A Window Into LLMs | Sparse Autoencoders Explained

What Happened With Sparse Autoencoders?

VISION SPARSE AUTOENCODERS: Overview + Walkthrough of Running an SAE

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

What is Gemma Scope?

Transcoders Beat Sparse Autoencoders for Interpretability

Sparse Autoencoders Unlearn Knowledge in LLMs | A Paper-Based Walkthrough

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders

View Detailed Profile

SAEs | Gemma Scope: Open Sparse Autoencoders for Language Model Interpretability

SAEs | Gemma Scope: Open Sparse Autoencoders for Language Model Interpretability

Sparse autoencoders

Demo: Gemma Scope: Sparse autoencoders on Gemma 2

Demo: Gemma Scope: Sparse autoencoders on Gemma 2

Sparse Autoencoders

Gemma Scope demo with Neuronpedia

Gemma Scope demo with Neuronpedia

Explore Neuronpedia, an

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

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

https://arxiv.org/abs//2408.05147 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers ...

A Window Into LLMs | Sparse Autoencoders Explained

A Window Into LLMs | Sparse Autoencoders Explained

This has been my favorite video so far to make! I think

What Happened With Sparse Autoencoders?

What Happened With Sparse Autoencoders?

Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ...

VISION SPARSE AUTOENCODERS: Overview + Walkthrough of Running an SAE

VISION SPARSE AUTOENCODERS: Overview + Walkthrough of Running an SAE

In this video, we explore how Vision

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

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

https://arxiv.org/abs//2408.05147 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers ...

What is Gemma Scope?

What is Gemma Scope?

Explore

Transcoders Beat Sparse Autoencoders for Interpretability

Transcoders Beat Sparse Autoencoders for Interpretability

Transcoders Beat

Sparse Autoencoders Unlearn Knowledge in LLMs | A Paper-Based Walkthrough

Sparse Autoencoders Unlearn Knowledge in LLMs | A Paper-Based Walkthrough

I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders

Protein

Introduction to Sparse AutoEncoders | ML@P Reading Group | Jinen Setpal

Introduction to Sparse AutoEncoders | ML@P Reading Group | Jinen Setpal

Slides: https://jinen.setpal.net/slides/sae.pdf.