INDEX

Explanations

the word "and", especially when following a list or conditions

oai_token-act-pair · gemini-2.0-flash

and

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

 purpoſe

-0.70

ſelf

-0.68

?]

-0.63

IsContent

-0.62

 faſt

-0.61

 Inscrivez

-0.60

 createState

-0.59

 ſame

-0.57

 كومونز

-0.57

POSITIVE LOGITS

adə

0.55

 Hood

0.50

 रेटिंग

0.50

plotlib

0.49

ंदीखरीदारी

0.49

mainwindow

0.48

cosystem

0.48

 CanadaChoose

0.47

iseerd

0.47

merz

0.47

Activations Density 2.433%

the word "and", especially when following a list or conditions

and

No Comments

No Known Activations