INDEX

Explanations

numerical data and familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ArgsConstructor

-0.58

itespace

-0.54

År

-0.53

OGND

-0.52

存于互联网档案馆

-0.51

SourceChecksum

-0.50

getDoctrine

-0.48

homonymie

-0.48

Academics

-0.48

neurial

-0.47

POSITIVE LOGITS

 grand

0.74

 grandchildren

0.72

 great

0.67

 Grand

0.65

 Great

0.61

 predeceased

0.57

grandchildren

0.56

grand

0.56

 grandchild

0.56

 Bund

0.56

Activations Density 0.028%

numerical data and familial relationships

No Comments

No Known Activations