INDEX

Explanations

text related to contests or giveaways

oai_token-act-pair · gpt-3.5-turbo

phrases related to opportunities or chances to win

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

 thereto

-0.43

 therein

-0.41

 analytic

-0.41

 thereof

-0.41

 thereafter

-0.41

sylv

-0.41

 plaus

-0.39

 insofar

-0.38

 neoc

-0.37

Reports

-0.37

POSITIVE LOGITS

byss

0.51

 Underworld

0.47

 Extras

0.44

APP

0.42

xual

0.42

 Gorge

0.42

Hun

0.40

è¦ļéĨĴ

0.40

æ©

0.40

Hak

0.39

Activations Density 3.950%

text related to contests or giveaways

phrases related to opportunities or chances to win

No Comments

No Known Activations