INDEX

Explanations

phrases related to medicine and healthcare products

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

complexContent

-0.53

upyter

-0.51

odyne

-0.49

colari

-0.46

eaway

-0.42

populations

-0.42

 onAnimation

-0.42

له

-0.42

 Populations

-0.42

 barra

-0.42

POSITIVE LOGITS

MENAFN

0.76

AndEndTag

0.74

featureID

0.72

 ostavi

0.70

 مشين

0.66

 JpaRepository

0.63

<?

0.59

SourceChecksum

0.59

 betweenstory

0.59

 asciug

0.59

Activations Density 0.005%

phrases related to medicine and healthcare products

No Comments

No Known Activations