INDEX

Explanations

question prompts in a document

oai_token-act-pair · gemini-2.0-flash

questions and activities

np_max-act · 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

providedIn

-0.60

cshtml

-0.59

GraphicsUnit

-0.56

TestBed

-0.54

bootstrapcdn

-0.51

 Мексичка

-0.50

UserScript

-0.50

 يتيمه

-0.50

wee

-0.48

 cherchés

-0.48

POSITIVE LOGITS

audiovisuel

0.55

AsUp

0.54

webtoken

0.53

AccessorTable

0.52

asties

0.52

PRNewswire

0.50

Autoritní

0.48

 juſ

0.47

RTSN

0.46

PRWEB

0.46

Activations Density 0.152%

question prompts in a document

questions and activities

No Comments

No Known Activations