INDEX

Explanations

mentions of the United States frequently abbreviated as "U.S."

oai_token-act-pair · gemini-2.0-flash

occurrences of the letter 'U'

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

U.S. mentions

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

und

-0.50

 bouch

-0.46

setPointSize

-0.42

onViewCreated

-0.41

 beyond

-0.41

 sống

-0.41

jos

-0.40

ไว

-0.39

createCell

-0.39

STROKE

-0.38

POSITIVE LOGITS

saraba

0.75

 zelve

0.71

ValueStyle

0.71

 disambiguazione

0.69

 незавершена

0.69

 stället

0.68

tableFuture

0.66

]--;

0.65

 متعلقه

0.63

 Pingback

0.61

Activations Density 0.187%

mentions of the United States frequently abbreviated as "U.S."

occurrences of the letter 'U'

U.S. mentions

No Comments

No Known Activations