INDEX

Explanations

numbers and numerical data

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

Code snippets or unique technical terms

np_acts-logits-general · gemini-2.0-flash

case or friendship

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 élevées

-0.63

pulumi

-0.59

 wzgl

-0.59

 <<<<<<<<<<<<<<

-0.58

 szív

-0.57

odule

-0.57

msgTypes

-0.56

setof

-0.55

éc

-0.55

RegressionTest

-0.55

POSITIVE LOGITS

esModule

0.62

ConstraintMaker

0.59

 صوتيه

0.56

 dataSnapshot

0.56

})*/

0.55

}}}

0.55

MethodManager

0.55

хьтан

0.55

}}

0.54

ритори

0.54

Activations Density 0.080%

numbers and numerical data

Code snippets or unique technical terms

case or friendship

No Comments

No Known Activations