INDEX

Explanations

words and phrases expressing doubt or hedging

oai_token-act-pair · gemini-2.0-flash

say "that"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Mémoires

-0.42

JspWriter

-0.41

 however

-0.40

//~

-0.39

 vuelto

-0.38

 avoit

-0.38

dyž

-0.37

 caneta

-0.37

 helst

-0.37

 disponibilità

-0.37

POSITIVE LOGITS

PerformLayout

0.69

we

0.68

<bos>

0.67

IsMutable

0.64

 defaultstate

0.64

 Италијани

0.63

sizeCache

0.63

DeleteBehavior

0.62

ModelAdmin

0.61

出版年

0.61

Activations Density 3.453%

words and phrases expressing doubt or hedging

say "that"

No Comments

No Known Activations