INDEX

Explanations

instances of the year 2001 and references to dates and events related to that year

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

Dates with the year

np_acts-logits-general · gemini-2.0-flash

dates and comments

np_acts-logits-general · gemini-2.5-flash-lite

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

)");

-0.70

jmniej

-0.69

};*/

-0.68

 CanadaChoose

-0.66

 Chwiliwch

-0.65

=$?

-0.65

 мәкалә

-0.65

AnimationsModule

-0.65

featureID

-0.63

 otomatig

-0.62

POSITIVE LOGITS

//$

0.54

0.51

ppuden

0.44

Ẽ

0.44

CLING

0.43

 ader

0.40

//

0.40

postValue

0.40

癸

0.39

ソル

0.39

Activations Density 0.150%

instances of the year 2001 and references to dates and events related to that year

Dates with the year

dates and comments

No Comments

No Known Activations