INDEX

Explanations

elements related to structured data presentation, particularly in academic or technical documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

曖昧さ回避

-0.83

 gainera

-0.81

RTLD

-0.80

]=>

-0.80

styleType

-0.79

OrBuilder

-0.77

 дописавши

-0.76

 Normdatei

-0.76

:✨

-0.74

lgari

-0.72

POSITIVE LOGITS

 Latvian

0.56

ship

0.51

 Estonian

0.51

 Prussian

0.50

英語版

0.50

 whee

0.49

 Cornelia

0.48

 tiegħek

0.48

 vastu

0.48

一見

0.48

Activations Density 0.146%

elements related to structured data presentation, particularly in academic or technical documents

No Comments

No Known Activations