INDEX

Explanations

statements about personal experiences or attitudes

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

Quotation marks and "We"

np_acts-logits-general · gemini-2.0-flash

We feel

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

};*/

-0.60

liminaries

-0.54

*/;

-0.54

 biß

-0.54

)*/

-0.52

HasValue

-0.52

standers

-0.51

,:);

-0.48

daß

-0.48

 defaultstate

-0.48

POSITIVE LOGITS

 AssemblyCulture

0.81

 kasarigan

0.76

IntoConstraints

0.75

 InputDecoration

0.72

XmlAccessType

0.72

jsxFileName

0.71

aarrggbb

0.69

piram

0.69

 متعلقه

0.68

principalColumn

0.68

Activations Density 0.077%

statements about personal experiences or attitudes

Quotation marks and "We"

We feel

No Comments

No Known Activations