INDEX

Explanations

words and phrases indicating disagreement with authority

oai_token-act-pair · gemini-2.0-flash

foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ంద

-0.47

 procede

-0.43

 démo

-0.42

otten

-0.42

didSet

-0.42

 Wadsworth

-0.40

 فق

-0.40

 letra

-0.40

 Ritter

-0.37

 répondit

-0.37

POSITIVE LOGITS

hoeddwyd

0.84

oa̍t

0.81

 تضيفلها

0.80

Personendaten

0.77

ьаж

0.73

esModule

0.70

encodeWith

0.66

NOPQRST

0.65

UrlResolution

0.65

PhysRevD

0.65

Activations Density 26.420%

words and phrases indicating disagreement with authority

foreign words

No Comments

No Known Activations