INDEX

Explanations

references to augmented reality and its functionalities

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

Follows "AR" or "<start_of_turn>user"

np_acts-logits-general · gemini-2.0-flash

augmented reality function

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

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

AnchorStyles

-0.54

rungsseite

-0.52

pushFollow

-0.51

 متعلقه

-0.45

appé

-0.45

pegno

-0.44

HostException

-0.43

GraphicsUnit

-0.43

IVEREF

-0.42

atience

-0.42

POSITIVE LOGITS

Pokémon

0.44

 Pokémon

0.41

WebElementEntity

0.39

évaluateur

0.38

hender

0.38

 Pokemon

0.38

="@+

0.37

Děkuji

0.37

InputBorder

0.36

NewUrlParser

0.35

Activations Density 0.209%

references to augmented reality and its functionalities

Follows "AR" or "<start_of_turn>user"

augmented reality function

No Comments

No Known Activations