INDEX

Explanations

words and phrases related to programming, social networks and collaborative groups

oai_token-act-pair · gemini-2.0-flash

coding & lists

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

bootstrapcdn

-0.66

<eos>

-0.53

acty

-0.50

ForKey

-0.48

[:,

-0.47

TagHelpers

-0.46

toHaveBeenCalled

-0.45

Now

-0.44

 Entsch

-0.43

POSITIVE LOGITS

脚注の使い方

0.77

 насељу

0.75

 myſelf

0.69

 Catawiki

0.65

 autorytatywna

0.64

 NUKAT

0.62

 Jefus

0.62

oplasty

0.60

0.59

 tartalomajánló

0.59

Activations Density 2.102%

words and phrases related to programming, social networks and collaborative groups

coding & lists

No Comments

No Known Activations