INDEX

Explanations

phrases related to receiving updates and special offers

oai_token-act-pair · gpt-3.5-turbo

phrases related to receiving updates or notifications

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

verning

-0.85

avery

-0.79

tein

-0.77

odor

-0.76

eur

-0.75

rifice

-0.75

gha

-0.72

zh

-0.71

iac

-0.70

nered

-0.70

POSITIVE LOGITS

 notifications

0.95

 updates

0.95

 Updates

0.88

 update

0.85

 notification

0.82

ilver

0.80

 alerts

0.80

mith

0.73

 Notification

0.73

 announcements

0.73

Activations Density 0.017%

phrases related to receiving updates and special offers

phrases related to receiving updates or notifications

No Comments

No Known Activations