INDEX

Explanations

details related to processes, events, and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

存于互联网档案馆

-0.66

 pageContext

-0.60

__':

-0.57

kloped

-0.57

ableView

-0.56

 AttributeSet

-0.56

Hozzáférés

-0.55

</>

-0.55

 <<<<<<<<<<<<<<

-0.52

"?>

-0.52

POSITIVE LOGITS

ariConfig

0.56

ällig

0.53

addCriterion

0.50

helves

0.49

 appunto

0.48

ыгана

0.48

 therefore

0.47

 olduğu

0.47

<bos>

0.47

getHours

0.47

Activations Density 0.454%

details related to processes, events, and their descriptions

No Comments

No Known Activations