INDEX

Explanations

references to prominent individuals and their actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 localidad

-0.37

 réc

-0.36

 térm

-0.35

 économ

-0.34

зонта

-0.33

 Waite

-0.32

Foreground

-0.32

Modern

-0.32

 ladrillo

-0.32

 Jerusalén

-0.32

POSITIVE LOGITS

webElement

0.75

PMailer

0.61

 ligiloj

0.55

 الرياضيه

0.52

RectangleBorder

0.51

 BorderSide

0.50

期刊论文

0.50

 masked

0.49

嘧

0.48

 serpentine

0.47

Activations Density 0.052%

references to prominent individuals and their actions or statements

No Comments

No Known Activations