INDEX

Explanations

formal expressions of gratitude and appreciation, often involving names or titles and exclamations.

oai_token-act-pair · gemini-2.0-flash

programming-related terms

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

foreign words

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

 thanks

-1.10

 Thanks

-1.07

Thanks

-1.02

thanks

-1.00

 THANKS

-0.86

Díky

-0.71

 grâce

-0.70

Thx

-0.69

 gracias

-0.68

THANKS

-0.68

POSITIVE LOGITS

 مشين

0.72

 ProtoMessage

0.66

ApiModelProperty

0.62

thâu

0.59

 ujednoznacz

0.58

EditorBrowsable

0.57

slidesToShow

0.56

بوابة

0.55

ölker

0.52

BoxShadow

0.51

Activations Density 0.967%

formal expressions of gratitude and appreciation, often involving names or titles and exclamations.

programming-related terms

foreign words

No Comments

No Known Activations

formal expressions of gratitude and appreciation, often involving names or titles and exclamations.

programming-related terms

foreign words

No Comments

No Known Activations