INDEX

Explanations

terms related to health issues and medical risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddHtmlAttribute

-0.58

ณี

-0.49

horabuena

-0.48

 realista

-0.43

nickel

-0.42

ichthys

-0.42

olito

-0.42

 tartalomajánló

-0.42

€¢

-0.41

webb

-0.41

POSITIVE LOGITS

AndroidJUnit

0.80

IVEREF

0.78

 esternos

0.73

 betweenstory

0.71

RefNanny

0.69

verwijspagina

0.66

ViewFeatures

0.65

simpleType

0.63

RuleContext

0.63

SpringBootTest

0.62

Activations Density 0.219%

terms related to health issues and medical risks

No Comments

No Known Activations