INDEX

Explanations

references to movies, actors, and significant film industry terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 kasarigan

-0.76

MemoryWarning

-0.68

viewDidLoad

-0.58

AnchorStyles

-0.56

binant

-0.54

findpost

-0.54

/***/

-0.50

laye

-0.49

setts

-0.48

//

-0.47

POSITIVE LOGITS

 protoimpl

0.88

 JAXBElement

0.83

Aholisi

0.82

SharedDtor

0.79

 فريبيس

0.78

Jereo

0.78

 ligiloj

0.76

ſelves

0.76

lapsingToolbar

0.76

 الرياضيه

0.76

Activations Density 1.466%

references to movies, actors, and significant film industry terms

No Comments

No Known Activations