INDEX

Explanations

patterns related to using "other than" to exclude specific options or possibilities

oai_token-act-pair · gpt-3.5-turbo

references to alternatives or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

abad

-0.55

||||

-0.52

 Bohem

-0.52

 Latest

-0.51

ogy

-0.50

(){

-0.50

}}}

-0.50

ii

-0.49

Et

-0.48

ogie

-0.48

POSITIVE LOGITS

 than

1.55

than

1.25

worldly

1.18

 Than

1.15

ially

0.95

 then

0.86

wise

0.81

ials

0.78

wcs

0.78

 THEN

0.77

Activations Density 0.073%

patterns related to using "other than" to exclude specific options or possibilities

references to alternatives or exceptions

No Comments

No Known Activations