Neel Nanda

12.6K subscribers

48 videos

View on YouTube

Latest Videos

How Aligned Is Claude A Live Review of the Opus 4.5 System Card

How Aligned Is Claude A Live Review of the Opus 4.5 System Card

Neel Nanda

2.7K views·4 months ago

Bitter Lesson-Pilled Interp A Live Paper Review (Activation Oracles & PCD)

Bitter Lesson-Pilled Interp A Live Paper Review (Activation Oracles & PCD)

Neel Nanda

3.8K views·4 months ago

Creating Models Worth Interpreting

Creating Models Worth Interpreting

Neel Nanda

2.1K views·5 months ago

How Reasoning Models Break Mechanistic Interpretability Techniques

How Reasoning Models Break Mechanistic Interpretability Techniques

Neel Nanda

3.5K views·5 months ago

Can Interpretability Control Model Training

Can Interpretability Control Model Training

Neel Nanda

1.4K views·5 months ago

Science of Misalignment

Science of Misalignment

Neel Nanda

1.7K views·5 months ago

How Will Mech Interp Help Make AGI Safe

How Will Mech Interp Help Make AGI Safe

Neel Nanda

2.1K views·6 months ago

What Matters Right Now In Mechanistic Interpretability

What Matters Right Now In Mechanistic Interpretability

Neel Nanda

6.3K views·6 months ago

What Happened With Sparse Autoencoders

What Happened With Sparse Autoencoders

Neel Nanda

7.6K views·6 months ago

The Story of Mech Interp

The Story of Mech Interp

Neel Nanda

6.3K views·6 months ago

What do models learn during finetuning A model diffing paper walkthrough w Clement & Julian

What do models learn during finetuning A model diffing paper walkthrough w Clement & Julian

Neel Nanda

4.0K views·6 months ago

Can LLMs Introspect A Live Paper Review

Can LLMs Introspect A Live Paper Review

Neel Nanda

3.5K views·6 months ago

How To Interpret Chain Of Thought A Walkthrough

How To Interpret Chain Of Thought A Walkthrough

Neel Nanda

4.3K views·9 months ago

How To Think About Thinking Models

How To Think About Thinking Models

Neel Nanda

9.7K views·1 year ago

Neel Does Research (Vibe Coding Edition)

Neel Does Research (Vibe Coding Edition)

Neel Nanda

7.7K views·1 year ago

4 Philosophies of Interpretability

4 Philosophies of Interpretability

Neel Nanda

3.0K views·1 year ago

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 23

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 23

Neel Nanda

1.6K views·2 years ago

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 33

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 33

Neel Nanda

489 views·2 years ago

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 13

A Walkthrough of Copy Suppression w Callum McDougall, Arthur Conmy & Cody Rushing Part 13

Neel Nanda

2.0K views·2 years ago

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 13

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 13

Neel Nanda

4.5K views·2 years ago

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 23

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 23

Neel Nanda

1.4K views·2 years ago

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 33

A Walkthrough of Automated Circuit Discovery w Arthur Conmy Part 33

Neel Nanda

835 views·2 years ago

Realtime Research Walkthrough Parenthesis Balancing in 1L Toy Language Model (Part 2)

Realtime Research Walkthrough Parenthesis Balancing in 1L Toy Language Model (Part 2)

Neel Nanda

901 views·2 years ago

Realtime Research Walkthrough Parenthesis Balancing in 1L Toy Language Model (Part 1)

Realtime Research Walkthrough Parenthesis Balancing in 1L Toy Language Model (Part 1)

Neel Nanda

1.8K views·2 years ago

Real-Time Research Walkthrough Mover Heads Part 22

Real-Time Research Walkthrough Mover Heads Part 22

Neel Nanda

901 views·2 years ago

Real-Time Research Walkthrough Mover Heads Part 12

Real-Time Research Walkthrough Mover Heads Part 12

Neel Nanda

6.1K views·2 years ago

Real-Time Research Walkthrough Addition in GPT-J

Real-Time Research Walkthrough Addition in GPT-J

Neel Nanda

2.9K views·2 years ago

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 13

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 13

Neel Nanda

2.3K views·2 years ago

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 23

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 23

Neel Nanda

954 views·2 years ago

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 33

A Walkthrough of Finding Neurons In A Haystack w Wes Gurnee Part 33

Neel Nanda

734 views·2 years ago

Load More Videos

Neel Nanda - NatokHD | NatokHD