INDEX

Explanations

terms and phrases related to medical metrics and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Viator

-0.58

GLS

-0.53

 surpluses

-0.52

 rhetor

-0.50

 informée

-0.48

 snork

-0.47

FundMe

-0.47

 שוליים

-0.46

 minded

-0.46

 parietal

-0.45

POSITIVE LOGITS

mybatisplus

0.81

">//

0.78

بوابة

0.77

InjectAttribute

0.73

 незавершена

0.73

AutoField

0.67

 pinulongan

0.67

+#+#

0.66

__':

0.66

 ligiloj

0.66

Activations Density 0.651%

terms and phrases related to medical metrics and statistics

No Comments

No Known Activations