INDEX

Explanations

references to scientific journals and publications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

OGND

-0.90

Ārējās

-0.86

sizeCache

-0.68

 ModelExpression

-0.67

::_('

-0.65

 ErrIntOverflow

-0.63

 Rajah

-0.55

 Maladies

-0.55

JspWriter

-0.55

Hentet

-0.54

POSITIVE LOGITS

PhysRevLett

0.65

mybatisplus

0.62

 Bacteriol

0.61

发表于

0.58

Билгалдахарш

0.56

twimg

0.54

uminense

0.54

brtc

0.53

PRNewswire

0.52

openqa

0.52

Activations Density 0.255%

references to scientific journals and publications

No Comments

No Known Activations