INDEX

Explanations

documentation comments and annotations for functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

styleType

-0.62

BagLayout

-0.62

::_('

-0.59

 INTERESAR

-0.59

AlterField

-0.57

createCanvas

-0.57

parsedMessage

-0.56

__':

-0.54

 Kluwer

-0.53

lgari

-0.52

POSITIVE LOGITS

">//

0.72

TintMode

0.69

})();

0.65

"><?=

0.64

 appunt

0.62

 Kers

0.61

 noires

0.60

@"/

0.60

Personensuche

0.59

 flecha

0.59

Activations Density 0.045%

documentation comments and annotations for functions and parameters

No Comments

No Known Activations