INDEX

Explanations

references to lists and organization in content

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

lists or following introductory phrases

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

 للاسماء

-0.67

reportWebVitals

-0.52

الإنجليزية

-0.51

SharedDtor

-0.51

 فريبيس

-0.51

الدراسه

-0.49

ьаж

-0.49

المشاركات

-0.48

 AttributeSet

-0.48

 transférez

-0.47

POSITIVE LOGITS

Below

0.63

 below

0.59

 Below

0.57

below

0.57

 Berikut

0.49

 abaixo

0.47

 list

0.45

list

0.44

下面

0.44

以下是

0.44

Activations Density 0.061%

references to lists and organization in content

lists or following introductory phrases

No Comments

No Known Activations