INDEX

Explanations

mathematical formatting and notations

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

code and mathematics

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

rawDesc

-0.33

$\%

-0.31

 Fifth

-0.30

VolleyError

-0.30

 aside

-0.29

("")]

-0.29

TestingModule

-0.28

cab

-0.28

 fifth

-0.28

 disponibilités

-0.28

POSITIVE LOGITS

GEBURTSDATUM

0.71

 propOrder

0.54

 Italijanski

0.52

➟

0.52

indépendance

0.51

PCell

0.51

Portail

0.50

 VIAF

0.50

inaison

0.49

setAccessible

0.47

Activations Density 0.176%

mathematical formatting and notations

code and mathematics

No Comments

No Known Activations