INDEX

Explanations

phrases related to artistic or professional accomplishments

oai_token-act-pair · gpt-3.5-turbo

references to the work and contributions of artists or creators

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

 Ukrain

-0.95

wcs

-0.70

 Rohing

-0.66

 Predators

-0.64

 Diet

-0.62

 Comfort

-0.62

ylon

-0.62

 champagne

-0.61

 snap

-0.61

Args

-0.61

POSITIVE LOGITS

 ethic

1.40

flows

1.24

station

1.20

aday

1.07

horse

1.07

manship

1.05

bench

1.02

fare

0.94

mates

0.93

mate

0.89

Activations Density 0.048%

phrases related to artistic or professional accomplishments

references to the work and contributions of artists or creators

No Comments

No Known Activations