INDEX

Explanations

a complex pattern of words, including verbs of existence, conjunctions, prepositions, and other words

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Autoritní

-0.84

 ReactDOM

-0.78

twimg

-0.75

 виправивши

-0.75

ArgumentParser

-0.72

RetentionPolicy

-0.71

ionario

-0.70

Geplaatst

-0.70

toPromise

-0.68

 Reverso

-0.68

POSITIVE LOGITS

 vectorielles

0.59

 crescere

0.50

 cardiaque

0.49

 ecuator

0.46

 duquel

0.46

 électroniques

0.45

 supplémentaire

0.44

 décider

0.43

jeh

0.43

ULDER

0.43

Activations Density 0.999%

a complex pattern of words, including verbs of existence, conjunctions, prepositions, and other words

No Comments

No Known Activations

a complex pattern of words, including verbs of existence, conjunctions, prepositions, and other words

No Comments

No Known Activations