INDEX

Explanations

references to geographic locations and historical territories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 >=",

-0.60

mybatisplus

-0.59

 PyTuple

-0.58

 numberOfRows

-0.56

}();

-0.56

 advogado

-0.56

Datuak

-0.55

 resourceCulture

-0.53

Cartney

-0.53

 varandra

-0.52

POSITIVE LOGITS

 region

0.67

 Region

0.64

 Valley

0.62

 River

0.61

 Peninsula

0.60

 National

0.56

之

0.54

 Gera

0.54

crit

0.53

inspired

0.53

Activations Density 0.365%

references to geographic locations and historical territories

No Comments

No Known Activations