INDEX

Explanations

references to media, events, and entities involved in entertainment and culture

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

ItemBackground

-0.61

ViewFeatures

-0.59

 createState

-0.56

 culturelles

-0.54

uxxxx

-0.53

 transfieras

-0.53

GEBURTSDATUM

-0.53

ʺ

-0.52

AppComponent

-0.51

fällig

-0.50

POSITIVE LOGITS

 respectively

0.89

respectively

0.84

 both

0.73

 respectivamente

0.73

both

0.69

 alike

0.68

Both

0.65

 दोनों

0.65

 Both

0.63

両方

0.60

Activations Density 1.372%

references to media, events, and entities involved in entertainment and culture

No Comments

No Known Activations