INDEX

Explanations

words and short phrases in languages other than English

oai_token-act-pair · gemini-2.0-flash

factual statements or information

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

multiple languages

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

now

-0.72

 still

-0.68

 even

-0.67

 maintenant

-0.65

 just

-0.63

 natuurlijk

-0.62

 also

-0.60

 tampoco

-0.60

 simplemente

-0.58

 fortfarande

-0.58

POSITIVE LOGITS

 fact

0.66

 Wikimedijinoj

0.60

})).

0.60

 minute

0.59

 Theſe

0.56

 worst

0.56

 Cæsar

0.53

 ivelany

0.52

 truth

0.50

fact

0.50

Activations Density 1.352%

words and short phrases in languages other than English

factual statements or information

multiple languages

No Comments

No Known Activations