INDEX

Explanations

terms related to data, databases, and administrative processes

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

 surla

-0.56

سطس

-0.49

űr

-0.49

IndentedString

-0.48

 گزارش

-0.47

 مواليد

-0.47

олові

-0.46

ParallelGroup

-0.46

出版年

-0.45

SourceChecksum

-0.45

POSITIVE LOGITS

 interstate

0.81

 abroad

0.80

 afar

0.76

 geographically

0.73

遠く

0.73

 overseas

0.73

across

0.71

 zagran

0.69

 across

0.69

 distant

0.68

Activations Density 0.503%

terms related to data, databases, and administrative processes

No Comments

No Known Activations