INDEX

Explanations

programming terminology and structures, specifically related to object properties and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

serviceWorker

-0.56

WindowConstants

-0.51

acán

-0.51

|}{\

-0.47

hatikan

-0.46

AddRange

-0.46

ijas

-0.45

tra

-0.44

JvmStatic

-0.43

[]:

-0.43

POSITIVE LOGITS

ंदीखरीदारी

0.77

 ویکی‌پدی

0.69

OGND

0.67

InjectAttribute

0.66

 JpaRepository

0.62

 ویکی‌پدیا

0.59

AddHtmlAttribute

0.56

MMdd

0.56

 prossima

0.55

});*/

0.54

Activations Density 0.041%

programming terminology and structures, specifically related to object properties and function definitions

No Comments

No Known Activations