INDEX

Explanations

comparative words and phrases

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comparisons or negations of quantity and condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

?????

-0.71

EVA

-0.69

 vows

-0.64

alion

-0.64

 virginity

-0.62

 Chemistry

-0.61

 Advertisement

-0.60

Hom

-0.59

Vag

-0.56

anny

-0.56

POSITIVE LOGITS

 resembling

0.81

rir

0.74

»Ĵ

0.73

 describ

0.71

icter

0.71

seen

0.71

lio

0.69

aring

0.69

 Called

0.68

yond

0.68

Activations Density 0.444%

comparative words and phrases

phrases indicating comparisons or negations of quantity and condition

No Comments

No Known Activations