INDEX

Explanations

instances of the word "relate" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Autoritní

-0.85

 Waray

-0.75

Geplaatst

-0.72

 AppComponent

-0.71

لينكات

-0.67

WireFormat

-0.67

 незавершена

-0.66

Hentet

-0.65

 BitmapFactory

-0.63

Viited

-0.63

POSITIVE LOGITS

 related

1.72

related

1.47

 relate

1.47

 relating

1.45

 Related

1.44

 relates

1.41

relate

1.21

 RELATED

1.20

Related

1.17

 unrelated

1.15

Activations Density 0.154%

instances of the word "relate" and its variations

No Comments

No Known Activations