INDEX

Explanations

references to scientific publications and websites, specifically those related to medical or health topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 connection

-0.50

 semic

-0.49

 McPherson

-0.48

iserie

-0.48

{}

-0.47

 thượng

-0.47

بح

-0.47

PHEN

-0.46

 alertDialog

-0.46

AIRE

-0.46

POSITIVE LOGITS

sizeCache

0.78

EndContext

0.72

 يتيمه

0.71

ImageContext

0.70

 Мексичка

0.67

transQ

0.65

bootstrapcdn

0.65

CGRectMake

0.63

 WaitForSeconds

0.63

 ausgeschlossen

0.63

Activations Density 2.793%

references to scientific publications and websites, specifically those related to medical or health topics

No Comments

No Known Activations