INDEX

Explanations

references to specific scientific research terms or entities, particularly related to biochemical or pharmaceutical contexts

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

setupUi

-0.68

ViewFeatures

-0.58

省市镇

-0.56

alyptus

-0.55

VIRGO

-0.55

XmlAccessType

-0.54

 gainera

-0.53

 Италијани

-0.53

 CommonModule

-0.53

rhosis

-0.53

POSITIVE LOGITS

ValueStyle

0.59

 فريبيس

0.58

äsenti

0.54

NonQuery

0.54

 وتسجيلات

0.53

 gial

0.53

glVertex

0.53

 ناخن

0.52

 DISTRIBUTION

0.52

 CONDU

0.51

Activations Density 0.555%

references to specific scientific research terms or entities, particularly related to biochemical or pharmaceutical contexts

No Comments

No Known Activations