INDEX

Explanations

text suggesting features related to travel planning and navigation.

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

information related to travel and local amenities.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases related to providing or accessing information, particularly in the context of lists, details, or resources.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Information about dates and times

np_acts-logits-general · gemini-2.0-flash

schedules and availability

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

afficheront

-0.54

Wouldn

-0.48

ApiModel

-0.48

AppMethodBeat

-0.47

لبية

-0.46

tagHelperRunner

-0.43

 serez

-0.42

########.

-0.42

 appré

-0.41

fromCharCode

-0.41

POSITIVE LOGITS

 schedules

1.18

 schedule

1.16

 dates

1.11

 timings

1.08

 prices

1.07

 availability

1.00

 upcoming

0.98

 deadlines

0.97

 timetable

0.96

 Upcoming

0.95

Activations Density 0.243%