INDEX

Explanations

the prefix "un" combined with another letter or two

oai_token-act-pair · gemini-2.0-flash

occurrences of the prefix 'un'

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

un

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ंदीखरीदारी

-0.81

 kaarangay

-0.77

tagext

-0.74

ExtendWith

-0.70

AutoScaleMode

-0.69

awtextra

-0.68

AndEndTag

-0.66

VersionUID

-0.66

ArrowToggle

-0.66

 defaultstate

-0.64

POSITIVE LOGITS

 renseignements

0.50

<bos>

0.49

الدراسه

0.47

ıldığı

0.46

Cyfarwyddwr

0.46

vent

0.45

æn

0.44

 īpa

0.44

 naturales

0.43

 Hing

0.43

Activations Density 0.191%

the prefix "un" combined with another letter or two

occurrences of the prefix 'un'

un

No Comments

No Known Activations