INDEX

Explanations

legal terminology and copyright-related phrases

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

Licensing and warranty disclaimers

np_acts-logits-general · gemini-2.0-flash

license terms and warranties

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Tikang

-0.78

AndEndTag

-0.71

ValueStyle

-0.70

 Monfieur

-0.65

RegressionTest

-0.64

########.

-0.63

addCriterion

-0.63

vux

-0.62

msgTypes

-0.62

roek

-0.60

POSITIVE LOGITS

原始内容存档于

0.53

mapStateToProps

0.52

 الحره

0.49

niająca

0.48

?',

0.46

例文帳に追加

0.45

 rowspan

0.43

].)

0.43

かわらず

0.43

AlterField

0.43

Activations Density 0.006%

legal terminology and copyright-related phrases

Licensing and warranty disclaimers

license terms and warranties

No Comments

No Known Activations