INDEX

Explanations

mentions of travel and trips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 كمان

-0.48

prisma

-0.45

 Williams

-0.44

 Last

-0.44

Demografía

-0.44

нні

-0.43

﹠

-0.39

ligible

-0.39

 last

-0.39

ubakar

-0.39

POSITIVE LOGITS

 trip

1.36

 excursion

1.36

 excursions

1.36

 trips

1.35

 Trips

1.29

 travel

1.28

Trips

1.25

trip

1.22

 travels

1.20

 pilgri

1.20

Activations Density 0.168%

mentions of travel and trips

No Comments

No Known Activations