INDEX

Explanations

words indicating degree, quantity, group, or category.

oai_token-act-pair · gemini-2.0-flash

comparisons and differences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

脚注の使い方

-0.66

 незавершена

-0.65

出版年

-0.64

 '\\;'

-0.63

الحياه

-0.63

MemoryWarning

-0.61

########.

-0.61

 Waray

-0.59

İstinadlar

-0.58

abcdef

-0.57

POSITIVE LOGITS

 genomen

0.51

isière

0.49

WireFormatLite

0.48

so

0.47

 suci

0.47

 rêve

0.47

Capítulo

0.47

 comples

0.46

 Streak

0.46

 whom

0.46

Activations Density 6.671%

words indicating degree, quantity, group, or category.

comparisons and differences

No Comments

No Known Activations