INDEX

Explanations

interjections expressing emotion

oai_token-act-pair · gemini-2.0-flash

exclamations or emotional expressions

np_token-act-pair-logits · gpt-4o-mini

Interjections and foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HtmlAttribute

-0.94

 بيها

-0.74

RectangleBorder

-0.71

 CreateTagHelper

-0.68

setVerticalGroup

-0.68

QMetaType

-0.68

tableFuture

-0.67

CloseOperation

-0.66

 InputDecoration

-0.66

TabIndex

-0.64

POSITIVE LOGITS

ilités

0.39

 morena

0.38

 huelga

0.38

 envío

0.38

ddot

0.37

 nito

0.37

hpp

0.36

บ้าง

0.36

 pauvreté

0.36

]<<"

0.35

Activations Density 1.490%

interjections expressing emotion

exclamations or emotional expressions

Interjections and foreign words

No Comments

No Known Activations