INDEX

Explanations

mentions of the word "Pop" in different contexts

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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

perse

-0.65

externalActionCode

-0.64

IVES

-0.64

adr

-0.63

beit

-0.62

 Territory

-0.61

OME

-0.60

wcsstore

-0.60

 Benef

-0.59

 Correspond

-0.59

POSITIVE LOGITS

ulates

1.39

ulations

1.36

ulating

1.32

corn

1.31

ularity

1.28

ulated

1.21

ular

1.18

ulate

1.17

ULAR

1.08

ulation

1.05

Activations Density 0.030%

mentions of the word "Pop" in different contexts

references to "Pop" culture

No Comments

No Known Activations