INDEX

Explanations

structured data representations or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

 vors

-0.36

Javadoc

-0.33

sam

-0.33

料

-0.30

 page

-0.28

▬

-0.28

░░

-0.28

sson

-0.27

 rues

-0.27

 Samuel

-0.27

POSITIVE LOGITS

MessageTagHelper

0.72

Personensuche

0.72

0.71

Hentet

0.69

pecabe

0.69

 ExecuteAsync

0.66

Cyfarwyddwr

0.65

 يتيمه

0.65

autaire

0.64

 المعيارى

0.64

Activations Density 0.751%

structured data representations or formatting

No Comments

No Known Activations