INDEX

Explanations

formatting or structural elements within the text

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

return

-0.73

 return

-0.73

 returns

-0.68

 Return

-0.67

RefNanny

-0.65

 Returns

-0.65

 returning

-0.59

 returned

-0.57

Returns

-0.56

帰り

-0.55

POSITIVE LOGITS

ⓘ

0.86

continue

0.70

 חיצוניים

0.65

 ویکی‌پدیا

0.64

ieteur

0.63

NOPQRST

0.63

 virtuel

0.62

saraba

0.62

 Lordships

0.62

 Celestial

0.62

Activations Density 0.072%

formatting or structural elements within the text

No Comments

No Known Activations