INDEX

Explanations

mentions of Western Sahara, Sahrawi people, and related political terms

oai_token-act-pair · gemini-2.0-flash

Sahara

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Latvian

-0.43

RuleContext

-0.41

 zwar

-0.41

既

-0.41

usercontent

-0.41

 Norges

-0.41

 Dominion

-0.40

 Yankee

-0.40

 الرياضيه

-0.40

sp

-0.40

POSITIVE LOGITS

RectangleBorder

0.82

Parcelize

0.77

">//

0.73

 مشين

0.71

 ComVisible

0.71

 سكانية

0.71

 ویکی‌پدیا

0.71



0.69

 utafitiHapana

0.69

Efq

0.66

Activations Density 0.795%

mentions of Western Sahara, Sahrawi people, and related political terms

Sahara

No Comments

No Known Activations