INDEX

Explanations

references to things that are well-known or recognizable, especially those labeled as "famous" or "infamous"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 صفحۀ

-0.52

queryInterface

-0.49

 للمعارف

-0.40

investigation

-0.40

 herida

-0.39

AutoScaleMode

-0.39

 вполне

-0.38

Sicher

-0.38

tagPool

-0.38

Multiple

-0.38

POSITIVE LOGITS

 famous

1.88

famous

1.66

 Famous

1.60

Famous

1.59

 famosa

1.36

 berühmten

1.34

 famously

1.33

 famoso

1.32

 famed

1.29

 знамени

1.29

Activations Density 0.257%

references to things that are well-known or recognizable, especially those labeled as "famous" or "infamous"

No Comments

No Known Activations

references to things that are well-known or recognizable, especially those labeled as "famous" or "infamous"

No Comments

No Known Activations