INDEX

Explanations

references to object-oriented programming concepts, particularly involving the 'self' keyword

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 &___

-0.59

ؾ

-0.52

tinyos

-0.51

 Италијани

-0.51

tvguidetime

-0.50

ⓧ

-0.48

SharedDtor

-0.48

دانشنامهٔ

-0.47

elry

-0.47

pantalones

-0.47

POSITIVE LOGITS

RefNanny

0.47

WriteBarrier

0.38

 myself

0.37

weakSelf

0.37

 Ofen

0.35

me

0.34

WaitGroup

0.34

ExtendWith

0.34

myself

0.34

🙋

0.33

Activations Density 0.006%

references to object-oriented programming concepts, particularly involving the 'self' keyword

No Comments

No Known Activations