INDEX

Explanations

instances of the word "what," indicating a focus on questions or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Aze

-0.76

 brook

-0.74

 Verge

-0.72

 castor

-0.71

 Moors

-0.70

Brooks

-0.68

 Lucerne

-0.67

 Geor

-0.66

 BROOK

-0.66

timbangkan

-0.66

POSITIVE LOGITS

 what

1.81

 WHAT

1.70

what

1.67

WHAT

1.65

 What

1.65

What

1.65

wat

0.96

whats

0.95

Τι

0.94

 quelles

0.93

Activations Density 0.088%

instances of the word "what," indicating a focus on questions or inquiries

No Comments

No Known Activations