INDEX

Explanations

the occurrence of the word "que" in various forms, indicating its relevance in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-0.89

 contextLoads

-0.87

ρυσ

-0.81

 auffi

-0.80

 Chriſt

-0.79

 Majefty

-0.79

 myſelf

-0.77

 Jefus

-0.77

 himſelf

-0.76

conhe

-0.75

POSITIVE LOGITS

que

1.73

Que

1.56

Que

1.54

QUE

1.39

que

1.16

że

1.11

 què

0.99

QUE

0.95

Qué

0.92

__":

0.90

Activations Density 0.015%

the occurrence of the word "que" in various forms, indicating its relevance in sentences

No Comments

No Known Activations