INDEX

Explanations

phrases related to the benefits and implications of various subjects

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

erialized

-0.63

 Guin

-0.59

 Ronde

-0.58

 Euphrates

-0.58

 وتسجيلات

-0.58

Romeo

-0.57

 casse

-0.56

 autorytatywna

-0.56

Identi

-0.56

 Marlon

-0.56

POSITIVE LOGITS

щество

0.65

 having

0.60

sizeCache

0.59

 оригіналу

0.58

 betweenstory

0.58

asius

0.57

}*/

0.55

*/

0.55

use

0.55

wole

0.55

Activations Density 0.365%

phrases related to the benefits and implications of various subjects

No Comments

No Known Activations