INDEX

Explanations

the occurrences and variations of the letter 'm' in the text

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

m followed by Settings or Source

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 otomatig

-0.60

Tikang

-0.50

出版年

-0.47

XMLSchema

-0.44

fromCharCode

-0.42

 Taktlose

-0.42

principalTable

-0.42

 elseif

-0.40

VIAF

-0.39

DockStyle

-0.38

POSITIVE LOGITS

enetrable

0.54

argest

0.50

 Greg

0.50

 Mayan

0.49

$_['

0.48

 عمل

0.48

 microstructure

0.48

my

0.48

 Workforce

0.48

 Maya

0.47

Activations Density 0.006%

the occurrences and variations of the letter 'm' in the text

m followed by Settings or Source

No Comments

No Known Activations