INDEX

Explanations

words related to political unrest, especially violence, in specific geographic locations

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

dev

-0.54

◄

-0.48

ínez

-0.47

zös

-0.47

OGND

-0.47

SCOTT

-0.46

}{@

-0.44

 Maus

-0.44

 мәкал

-0.43

;/

-0.43

POSITIVE LOGITS

قایناقلار

0.62

Portail

0.58

HomeAsUpEnabled

0.56

Filmographie

0.56

Референце

0.55

évaluateur

0.54

AYSIA

0.54

colorbar

0.53

dispose

0.52

URIComponent

0.52

Activations Density 2.859%

words related to political unrest, especially violence, in specific geographic locations

No Comments

No Known Activations