INDEX

Explanations

phrases containing the word "wit."

oai_token-act-pair · gpt-3.5-turbo

instances of wit and cleverness in the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ŃĶ

-0.63

 tradem

-0.61

 obligated

-0.61

 predatory

-0.60

Ü

-0.59

ysis

-0.58

 stressful

-0.57

 Shuttle

-0.57

 lobbying

-0.57

Į

-0.56

POSITIVE LOGITS

hered

1.31

chery

1.11

sonian

0.86

glers

0.86

ener

0.83

nesses

0.81

combe

0.81

bol

0.81

wit

0.81

ician

0.78

Activations Density 0.011%

phrases containing the word "wit."

instances of wit and cleverness in the text

No Known Activations