INDEX

Explanations

numerical data or statistics

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

tables, numbers, or code diffs

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

istoitu

-0.49

 répertoire

-0.46

útbol

-0.41

ünst

-0.40

 réparer

-0.38

älv

-0.37

 morg

-0.37

tizia

-0.37

 wikipagina

-0.37

 règne

-0.37

POSITIVE LOGITS

 AssemblyTitle

0.69

 disambiguazione

0.63

AndEndTag

0.54

 تضيفلها

0.51

 ब्रेकडाउन

0.50

ContentAsync

0.50

webElementGuid

0.49

 Protobuf

0.48

IContainer

0.46

KommentareTeilen

0.45

Activations Density 0.000%

numerical data or statistics

tables, numbers, or code diffs

No Comments

No Known Activations