x

LESSWRONG

LW

Transformers — LessWrong

Transformers

This page is a stub.

Add Posts

1

1

Posts tagged Transformers

5

37Striking Implications for Learning Theory, Interpretability — and Safety?

2y

4

3

139How LLMs are and are not myopic

3y

16

2

232Modern Transformers are AGI, and Human-Level

2y

88

2

159[Linkpost] Interpreting Language Model Parameters

Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, mivanitskiy, Linda Linsefors, Lee Sharkey

10d

2

2

100LLMs Can't See Pixels or Characters

10mo

44

2

79Residual stream norms grow exponentially over the forward pass

StefanHex, TurnTrout

3y

24

2

62Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind

3y

12

2

58Concrete Steps to Get Started in Transformer Mechanistic Interpretability

3y

7

2

53How fast can we perform a forward pass?

4y

9

2

33AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them

2y

9

2

28How Do Induction Heads Actually Work in Transformers With Finite Capacity?

3y

0

2

17Training a Transformer to Compose One Step Per Layer (and Proving It)

19d

0

2

16How did ‘large’ language models get that way? The role of Transformers and Pretraining in GPT

12d

0

2

7If I ask an LLM to think step by step, how big are the steps?

2y

1

1

437Transformers Represent Belief State Geometry in their Residual Stream

2y

103

Load More (15/62)

Add Posts