INDEX

Explanations

words describing financial transactions, user accounts, and online banking

oai_token-act-pair · gemini-2.0-flash

financial terms and references to payment methods

np_token-act-pair-logits · gpt-4o-mini

user accounts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kaarangay

-0.68

بوابة

-0.65

AccessorTable

-0.64

waitKey

-0.63

 intptr

-0.62

GraphicsUnit

-0.60

moveToFirst

-0.60

tanleria

-0.60

Bakgrunnsstoff

-0.59

 Roskov

-0.59

POSITIVE LOGITS

enumi

0.59

ohu

0.49

 Ours

0.48

 đây

0.47

pushFollow

0.46

roveň

0.46

ngOnDestroy

0.46

birthdate

0.46

ölkerung

0.45

例句

0.45

Activations Density 1.153%

words describing financial transactions, user accounts, and online banking

financial terms and references to payment methods

user accounts

No Comments

No Known Activations