INDEX

Explanations

people in positions of authority and their actions

oai_token-act-pair · gemini-2.0-flash

[presumably foreign language, no clear pattern]

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ExecuteAsync

-0.65

قایناق‌لار

-0.56

Manbalar

-0.52

ագրություններ

-0.51

 }}">

-0.51

انيف

-0.50

èdia

-0.48

 дописавши

-0.48

 مشين

-0.48

GeoNames

-0.47

POSITIVE LOGITS

AndroidJUnit

0.68

 épis

0.63

 sélectionnés

0.62

 verticale

0.61

 refusé

0.60

 rêver

0.60

ืม

0.56

المناصب

0.55

 définiti

0.54

 sérieux

0.54

Activations Density 1.882%

people in positions of authority and their actions

[presumably foreign language, no clear pattern]

No Comments

No Known Activations