INDEX

Explanations

technical terms related to devices and their functionalities

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

AGU

-0.63

GIVEREF

-0.56

ⓧ

-0.53

 يتيمه

-0.51

Clik

-0.51

AndEndTag

-0.50

ꓕ

-0.50

WriteAttribute

-0.48

Ins

-0.47

tershire

-0.47

POSITIVE LOGITS

currentColor

0.39

centralwidget

0.35

 similar

0.34

 الحره

0.33

similar

0.32

tanleria

0.32

 createSprite

0.31

슷

0.31

 Taktlose

0.31

 similarly

0.31

Activations Density 0.974%

technical terms related to devices and their functionalities

No Comments

No Known Activations