INDEX

Explanations

words related to relationships, sharing, or connections between people, sometimes including code related words

oai_token-act-pair · gemini-2.0-flash

to

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

 resourceCulture

-0.82

曖昧さ回避

-0.81

CodedInputStream

-0.81

InvalidProtocol

-0.73

LookAnd

-0.68

rachtet

-0.66

Vidi

-0.66

:✨

-0.64

Tracce

-0.64

expandindo

-0.64

POSITIVE LOGITS

IBinder

0.52

 EventArgs

0.52

 complement

0.51

CloseOperation

0.48

addObject

0.47

 ElementRef

0.47

 help

0.45

 AttributeSet

0.45

津

0.44

Complement

0.44

Activations Density 1.724%

words related to relationships, sharing, or connections between people, sometimes including code related words

to

No Comments

No Known Activations

words related to relationships, sharing, or connections between people, sometimes including code related words

to

No Comments

No Known Activations