INDEX

Explanations

comments and annotations within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

AndEndTag

-0.55

 Pingback

-0.54

nachweis

-0.53

érale

-0.52

endpush

-0.51

readObject

-0.50

 مهر

-0.50

AutoScale

-0.48

NewReader

-0.47

 onBind

-0.47

POSITIVE LOGITS

بوابة

0.69

Portale

0.65

//

0.62

makeConstraints

0.61

 JADX

0.61

 useAuth

0.58

 gynhyrchwyd

0.57

SuppressMessage

0.57

 Fris

0.57

طقة

0.56

Activations Density 0.122%

comments and annotations within code

No Comments

No Known Activations