INDEX

Explanations

the use of the word "In" and variations of it within a sentence or paragraph

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

"In" followed by words related to brevity

np_acts-logits-general · gemini-2.0-flash

in short or clarified

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

ItemBackground

-0.87

 disambiguazione

-0.80

enderror

-0.72

 للاسماء

-0.72

UnknownFields

-0.69

IntoConstraints

-0.67

phrine

-0.66

Дереккөздер

-0.65

 '\\;'

-0.63

OrNil

-0.62

POSITIVE LOGITS

 short

2.58

short

2.18

Short

2.05

 Short

2.02

 SHORT

1.91

SHORT

1.81

短

1.44

 simple

1.43

 corto

1.38

 brief

1.36

Activations Density 0.279%

the use of the word "In" and variations of it within a sentence or paragraph

"In" followed by words related to brevity

in short or clarified

No Comments

No Known Activations