INDEX

Explanations

words related to government and politics

oai_token-act-pair · gemini-2.0-flash

foreign or specialized terms

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

Government organizations

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

Ligações

-0.67

 nakalista

-0.61

writeFieldEnd

-0.56

 ModelExpression

-0.52

tvguidetime

-0.52

Hauptartikel

-0.50

Slf

-0.50

 समीक्षक

-0.50

SceneManagement

-0.49

})();

-0.49

POSITIVE LOGITS

annica

0.68

 الحره

0.57

erai

0.55

 recensement

0.54

 Merle

0.52

BEAN

0.51

 typelib

0.50

atchewan

0.50

InstanceState

0.50

 ContentValues

0.49

Activations Density 0.485%

words related to government and politics

foreign or specialized terms

Government organizations

No Comments

No Known Activations