INDEX

Explanations

specific formatting or organization of text, particularly in code or structured data

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

preceding "line" or "lines"

np_acts-logits-general · gemini-2.0-flash

lines or line numbers

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

tvguidetime

-0.79

ItemBackground

-0.76

 للاسماء

-0.74

TemporalType

-0.73

TintMode

-0.68

featureID

-0.68

/*

-0.67

 AssemblyProduct

-0.66

StoryboardSegue

-0.66

ArrowToggle

-0.63

POSITIVE LOGITS

 lines

2.45

 line

2.38

 Lines

2.09

lines

1.97

 Line

1.97

Lines

1.93

line

1.92

Line

1.87

 LINES

1.79

 LINE

1.77

Activations Density 0.646%

specific formatting or organization of text, particularly in code or structured data

preceding "line" or "lines"

lines or line numbers

No Comments

No Known Activations