INDEX

Explanations

locations and references to geographical entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

})));

-0.67

InjectAttribute

-0.65

Personendaten

-0.62

ThroughAttribute

-0.61

migrationBuilder

-0.61

 незавершена

-0.57

])));

-0.57

Composable

-0.57

ViewFeatures

-0.55

complexContent

-0.55

POSITIVE LOGITS

 AssemblyCompany

0.62

 linkovi

0.52

ReusableCell

0.49

SBATCH

0.48

 العالم

0.48

ség

0.48

itonitis

0.48

GenerationType

0.47

 assoluto

0.47

Tembelea

0.45

Activations Density 0.116%

locations and references to geographical entities

No Comments

No Known Activations