INDEX

Explanations

acronyms, particularly those of organizations or standards

oai_token-act-pair · gemini-2.0-flash

A

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

TagHelper

-0.62

WriteBarrier

-0.50

 AssemblyCulture

-0.48

℗

-0.48

 onAnimation

-0.43

 menem

-0.42

 Follower

-0.42

 blik

-0.42

nsyn

-0.41

 Trekking

-0.40

POSITIVE LOGITS

<bos>

0.77

 незавершена

0.68

Lähteet

0.68

TagMode

0.66

 AllMovie

0.63

 useAppContext

0.62

 initComponents

0.58

énario

0.57

 kasarigan

0.56

getMenuInflater

0.56

Activations Density 0.751%

acronyms, particularly those of organizations or standards

A

No Comments

No Known Activations