E36 Untangling the Decision Making Process of Neural Networks - A Paper Deep Dive of Zoom In: An Introduction to Circuits
Artificially Unintelligent8 Marras 2023

E36 Untangling the Decision Making Process of Neural Networks - A Paper Deep Dive of Zoom In: An Introduction to Circuits

Mechanistic interpretability refers to understanding a model by looking at how its internal components function and interact with each other. It's about breaking down the model into its smallest functional parts and explaining how these parts come together to produce the model's outputs.

Neural networks are complex, making it hard to make broad, factual statements about their behavior. However, focusing on small, specific parts of neural networks, known as "circuits", might offer a way to rigorously investigate them. These "circuits" can be edited and analyzed in a falsifiable manner, making them potential foundations for understanding interpretability.

Zoom In looks at neural networks from a biological perspective looking at features and circuits to untangle their behaviors.

Do you still want to hear more from us? Follow us on the Socials:

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(52)

E49 Arxiv Dives: Retrieval Augmented Generation for Knowledge-Intensive NLP Tasks

E49 Arxiv Dives: Retrieval Augmented Generation for Knowledge-Intensive NLP Tasks

In this episode of the Artificially Unintelligent podcast, hosts William and Nicolay look into the paper "Retrieval Augmented Generation for Knowledge-intensive NLP Tasks." They discuss the significan...

17 Joulu 202320min

E48 Making LLM Training Easier with Hugging Face's TRL

E48 Making LLM Training Easier with Hugging Face's TRL

In this episode of the Artificially Unintelligent Podcast, hosts William and Nicolay delve into Hugging Face's Transformer Reinforcement Learning (TRL) library, discussing its impact and potential in ...

13 Joulu 202321min

E47 A Retrospective on OpenAI's Turbulent Weekend: Leadership, Breakthroughs, and Speculations

E47 A Retrospective on OpenAI's Turbulent Weekend: Leadership, Breakthroughs, and Speculations

In this episode of Artificially Unintelligent, hosts William and Nicolay dive into the dramatic events unfolding at OpenAI. They discuss the whirlwind of changes in leadership, starting with the unexp...

11 Joulu 202321min

E46 Unpacking FastAPI: Simplifying API Development in Python

E46 Unpacking FastAPI: Simplifying API Development in Python

In this episode of the Artificially Unintelligent Podcast, William and Nicolay explore the world of FastAPI, a dynamic web framework designed for building APIs with Python. They delve into the essenti...

10 Joulu 202319min

E45 Graphcast - How Google DeepMind is Changing Weather Forecasting

E45 Graphcast - How Google DeepMind is Changing Weather Forecasting

In this episode of the Artificially Unintelligent Podcast, William and Nicolay discuss the groundbreaking work of Google DeepMind on weather forecasting through their recent publication of the Graphca...

7 Joulu 202320min

Extra Gemini Unveiled: Google's Answer to GPT-4

Extra Gemini Unveiled: Google's Answer to GPT-4

In this extended episode of the Artificially Unintelligent Podcast, William and Nicolay delve into the exciting announcement of Google's new AI model, Gemini. They discuss Gemini's positioning as Goog...

7 Joulu 202329min

E44 AI’s New Building Blocks: What are Foundation Models?

E44 AI’s New Building Blocks: What are Foundation Models?

In this episode of Artificially Unintelligent, hosts William and Nicolay delve into the intricate world of foundation models in AI. They discuss what these models are – large-scale, machine learning m...

6 Joulu 202320min

E43 Diving Deep into Code Llama: The AI Coding Specialist

E43 Diving Deep into Code Llama: The AI Coding Specialist

In this episode of the Artificially Unintelligent Podcast, we delve into the fascinating world of Code Llama, a state-of-the-art large language model (LLM) that's reshaping the landscape of coding and...

25 Marras 202322min