INDEX

Explanations

the word "That" used to introduce a statement or an idea

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciples

-0.76

hips

-0.73

Occup

-0.69

ãĥīãĥ©

-0.68

arson

-0.67

ATURES

-0.65

 reciproc

-0.62

IDES

-0.61

Represent

-0.60

wage

-0.60

POSITIVE LOGITS

 fateful

0.90

 sounds

0.88

cher

0.87

 pesky

0.86

 sounded

0.78

 lasted

0.72

 nifty

0.71

 intrig

0.69

guy

0.69

 kind

0.68

Activations Density 0.176%

the word "That" used to introduce a statement or an idea

instances of the word "that."

No Comments

No Known Activations