INDEX

Explanations

words related to zombies and apocalyptic scenarios

oai_token-act-pair · gpt-3.5-turbo

terms related to zombies and zombie apocalypses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ional

-0.89

ours

-0.86

İ

-0.85

orney

-0.78

inion

-0.78

%]

-0.75

agall

-0.74

orie

-0.73

alty

-0.73

ibel

-0.72

POSITIVE LOGITS

 apocalypse

1.24

 horde

1.00

 Apocalypse

1.00

 hordes

0.94

ombies

0.92

 zombies

0.86

 zombie

0.84

 squid

0.84

 outbreak

0.82

 hunter

0.82

Activations Density 0.045%

words related to zombies and apocalyptic scenarios

terms related to zombies and zombie apocalypses

No Comments

No Known Activations