INDEX

Explanations

positive assessments of locations and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

󠁢

-0.60

PushMatrix

-0.55

 TabLayout

-0.50

QByteArray

-0.48

dne

-0.47

chium

-0.47

ningar

-0.45

 tombol

-0.44

mer

-0.44

tention

-0.44

POSITIVE LOGITS

 wireType

0.61

Expedia

0.60

dafx

0.58

 Expedia

0.56

出版年

0.56

parsedMessage

0.55

*/

0.54

})}

0.54

*/;

0.51

 étan

0.51

Activations Density 0.032%

positive assessments of locations and properties

No Comments

No Known Activations