INDEX

Explanations

content related to medical and pharmaceutical information, including studies and approval processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 mierda

-0.65

 kids

-0.63

-0.61

 simply

-0.60

don

-0.58

SerializedName

-0.58

 somehow

-0.57

</strong>

-0.57

 weirdly

-0.57

 everything

-0.55

POSITIVE LOGITS

 Meksiku

0.76

 Autorizaciones

0.76

 AppModule

0.74

MLLoader

0.73

 муніципалі

0.72

Aholisi

0.72

 мәкалә

0.68

 dépenses

0.67

 AssemblyCulture

0.67

 mourut

0.66

Activations Density 0.476%

content related to medical and pharmaceutical information, including studies and approval processes

No Comments

No Known Activations