INDEX

Explanations

geographical locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 незавершена

-0.56

клопе

-0.50

 transférez

-0.48

chequer

-0.48

berapa

-0.45

copal

-0.44

 Aruba

-0.44

 Baillargeon

-0.43

 كمان

-0.43

 Bumper

-0.43

POSITIVE LOGITS

 east

2.06

 west

2.04

 south

1.97

 north

1.95

 East

1.69

 southeast

1.66

north

1.63

 northwest

1.63

 northeast

1.62

east

1.61

Activations Density 0.227%

geographical locations and their descriptions

No Comments

No Known Activations