INDEX

Explanations

numerical values, particularly within mathematical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

asy

-0.50

ה

-0.45

ხ

-0.45

per

-0.45

щадь

-0.43

Her

-0.43

in

-0.43

werk

-0.42

mpto

-0.42

-0.41

POSITIVE LOGITS

 فريبيس

0.90

 resourceCulture

0.83

 AppModule

0.82

 AppCompatTheme

0.81

 NgModule

0.78

✨:

0.77

InitVars

0.75

lgari

0.73

berdayakan

0.73

NameInMap

0.72

Activations Density 1.075%

numerical values, particularly within mathematical or scientific contexts

No Comments

No Known Activations