INDEX

Explanations

references to specific health metrics, conditions, and organizations related to medical research and cardiovascular health

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

 ―――――

-0.71

 Coch

-0.67

Lid

-0.66

 Pank

-0.66

 Tant

-0.65

〢

-0.64

 ་་

-0.64

hdi

-0.64

 Yunnan

-0.63

 Greenland

-0.63

POSITIVE LOGITS

Buc

0.83

########.

0.79

Buc

0.77

UAE

0.69

 Lagos

0.69

Wiz

0.69

APORE

0.64

 Cincinnati

0.64

 Buhari

0.63

PHP

0.63

Activations Density 3.293%

references to specific health metrics, conditions, and organizations related to medical research and cardiovascular health

No Comments

No Known Activations