INDEX

Explanations

phrases related to tourism and travel trends.

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

phrases related to traveling and destinations.

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

phrases expressing uncertainty or speculation about future events or outcomes.

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

preceding "remains," "remain," or similar words

np_acts-logits-general · gemini-2.0-flash

whether remains

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صوتيه

-0.96

 للمعارف

-0.80

enterOuterAlt

-0.77

ImageContext

-0.77

ViewImports

-0.76

DoubleQuotes

-0.73

extAlignment

-0.73

 AssemblyCompany

-0.70

RenderAtEndOf

-0.70

ChildScrollView

-0.69

POSITIVE LOGITS

 remains

1.34

remains

1.05

 remain

1.03

 unclear

1.02

 depends

0.98

 Remains

0.84

 unknown

0.82

 остается

0.79

 remained

0.78

remain

0.77

Activations Density 0.365%