INDEX

Explanations

keywords related to popular culture, specifically "Pop"

oai_token-act-pair · gpt-3.5-turbo

references to "Pop" culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

OME

-0.73

EStreamFrame

-0.71

IVES

-0.69

externalActionCode

-0.68

%%%%

-0.68

perse

-0.66

wcsstore

-0.65

adr

-0.63

beit

-0.60

Ļ½

-0.60

POSITIVE LOGITS

corn

1.37

ulations

1.33

ulates

1.31

ulated

1.27

ulating

1.27

ular

1.25

ularity

1.25

ulate

1.18

lar

1.11

ulation

1.09

Activations Density 0.026%

keywords related to popular culture, specifically "Pop"

references to "Pop" culture

No Comments

No Known Activations