INDEX

Explanations

questions or statements related to curiosity or uncertainty

oai_token-act-pair · gpt-3.5-turbo

instances of the word "wondering."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ater

-0.58

roup

-0.57

Era

-0.55

Pro

-0.55

et

-0.55

 Lead

-0.54

 contained

-0.54

late

-0.53

 CONTR

-0.53

lay

-0.52

POSITIVE LOGITS

 wondering

3.46

 wondered

1.91

 wonder

1.85

 thinking

1.56

 hoping

1.54

 contemplating

1.50

 guessing

1.45

 fearing

1.40

 noticing

1.40

 curious

1.39

Activations Density 0.010%

questions or statements related to curiosity or uncertainty

instances of the word "wondering."

No Comments

No Known Activations