INDEX

Explanations

sequences of numbers and references, likely related to structured data or programming outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ModelExpression

-0.70

complexContent

-0.65

 Italijani

-0.59

webElementXpaths

-0.59

WithIOException

-0.58

Portály

-0.58

ņš

-0.56

mergeFrom

-0.54

yntaxException

-0.54

vux

-0.52

POSITIVE LOGITS

 оригіналу

0.62

 Soud

0.60

انيف

0.60

 textStatus

0.59

DeleteBehavior

0.57

ChildScrollView

0.56

 defStyle

0.56

postcss

0.56

󠁢

0.55

setupUi

0.54

Activations Density 0.254%

sequences of numbers and references, likely related to structured data or programming outputs

No Comments

No Known Activations