INDEX

Explanations

lists and phrases that include the word 'and' and/or 'more', especially when preceded by words indicating quantity

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 raiſ

-0.62

 rospy

-0.57

 Económica

-0.56

 myſelf

-0.56

Eſ

-0.56

 whoſe

-0.56

 houſe

-0.55

 themſelves

-0.54

RegistryLite

-0.53

uſ

-0.52

POSITIVE LOGITS

emark

0.53

plona

0.52

}{*}{

0.52

 lenker

0.50

 insuffisamment

0.50

WithFormat

0.49

ReusableCell

0.47

__(/*!

0.47

 BitmapFactory

0.47

RenderAtEndOf

0.47

Activations Density 2.898%

lists and phrases that include the word 'and' and/or 'more', especially when preceded by words indicating quantity

No Comments

No Known Activations