INDEX

Explanations

numerical values and specific formatting used in scientific papers and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.48

kre

-0.44

 growing

-0.39

ger

-0.38

ynes

-0.37

Da

-0.36

//

-0.35

require

-0.35

#!/

-0.34

 scroll

-0.34

POSITIVE LOGITS

المكان

0.97

OGND

0.96

 lenker

0.95

ьаж

0.94

دانشنامهٔ

0.93

 дописавши

0.91

 beginnetje

0.90

archiviato

0.90

 للاسماء

0.85

الحياه

0.85

Activations Density 0.377%

numerical values and specific formatting used in scientific papers and reports

No Comments

No Known Activations