INDEX

Explanations

phrases related to data regulations and labeling in the context of restaurants and businesses

oai_token-act-pair · gpt-3.5-turbo

words related to scientific terminology and research

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

ujah

-0.67

DragonMagazine

-0.65

ãĥ¯ãĥ³

-0.63

 prep

-0.62

é¾įå¥ĳå£«

-0.61

BuyableInstoreAndOnline

-0.61

atro

-0.59

unn

-0.58

RAL

-0.58

 humiliating

-0.58

POSITIVE LOGITS

tein

0.90

than

0.82

ħĭ

0.76

 Scrolls

0.71

leases

0.70

horn

0.68

itte

0.66

 Minion

0.65

bane

0.65

×ķ

0.64

Activations Density 0.793%

phrases related to data regulations and labeling in the context of restaurants and businesses

words related to scientific terminology and research

No Comments

No Known Activations