INDEX

Explanations

instances of the word "hide" 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

Negative Logits

 intptr

-0.75

曖昧さ回避

-0.70

 referrerpolicy

-0.67

adaptiveStyles

-0.62

Lähteet

-0.59

RectangleBorder

-0.58

cartier

-0.58

 honorary

-0.58

 pouss

-0.57

 giù

-0.57

POSITIVE LOGITS

WebVitals

0.76

Consequently

0.63

 Consequently

0.58

 concealed

0.58

 Klee

0.56

 particular

0.56

AccessException

0.56

pad

0.55

ventud

0.55

 hide

0.54

Activations Density 0.099%

instances of the word "hide" and its variations

No Known Activations