INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.73

 <<<<<<<<<<<<<<

-0.60

 ویکی‌پدی

-0.57

CDCl

-0.51

RTLD

-0.51

 Paglinawan

-0.50

bew

-0.50

 TRAV

-0.49

Autoritní

-0.49

 eccell

-0.48

POSITIVE LOGITS

AddTagHelper

0.85

FailureListener

0.75

bootstrapcdn

0.61

 TextInputType

0.58

ivably

0.57

lamabad

0.57

batore

0.56

[toxicity=0]

0.56

 GoogleFonts

0.55

withIdentifier

0.55

Activations Density 1.121%

No Comments

No Known Activations