INDEX

Explanations

words related to historical places or events, especially those involving graves/burial, conflict and or specific groups of people

oai_token-act-pair · gemini-2.0-flash

graves and memorials

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

DllImport

-0.54

verifyException

-0.54

 éclair

-0.50

págs

-0.50

 буенча

-0.50

Atsauces

-0.49

didSet

-0.49

newArrayList

-0.47

iglesia

-0.47

 dépla

-0.46

POSITIVE LOGITS

<bos>

0.84

StoryboardSegue

0.82

 betweenstory

0.81

FieldBuilder

0.68

AnchorTagHelper

0.67

 memorial

0.63

ViewImports

0.63

 kasarigan

0.60

 memorials

0.59

Memorials

0.58

Activations Density 0.649%

words related to historical places or events, especially those involving graves/burial, conflict and or specific groups of people

graves and memorials

No Comments

No Known Activations