INDEX

Explanations

references to administrative divisions or governmental entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

momentum

-0.46

EOL

-0.46

 الدولى

-0.46

modelBuilder

-0.45

 nationals

-0.45

věr

-0.45

 architecture

-0.45

 stored

-0.44

Stored

-0.44

 scenes

-0.44

POSITIVE LOGITS

 district

0.95

 municipality

0.91

 District

0.88

 districts

0.87

 Municipality

0.86

 municipalities

0.78

District

0.78

 Districts

0.78

 borough

0.78

district

0.78

Activations Density 0.537%

references to administrative divisions or governmental entities

No Comments

No Known Activations