INDEX

Explanations

phrases that indicate leadership and results

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ProtoMessage

-0.78

CloseOperation

-0.75

pausal

-0.73

 >=",

-0.73

BagConstraints

-0.70

terness

-0.70

 onCancelled

-0.70

 незавершена

-0.68

NameInMap

-0.66

cerely

-0.65

POSITIVE LOGITS

 rowspan

0.50

 때문

0.44

뀝

0.40

뀐

0.39

 there

0.39

ünst

0.38

뀔

0.38

 vertreten

0.38

 colpa

0.38

뀜

0.38

Activations Density 0.186%

phrases that indicate leadership and results

No Comments

No Known Activations