INDEX

Explanations

terms related to spacing and distance measurements in a physical or technical context

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

distance and spacing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

mphony

-0.44

 viewDidLoad

-0.44

叠

-0.43

Décès

-0.42

 miniaturka

-0.41

literal

-0.40

centralwidget

-0.40

Conclusie

-0.40

FormTagHelper

-0.39

DataPropertyName

-0.39

POSITIVE LOGITS

 Abstand

0.65

 spacing

0.64

 distance

0.61

 gaps

0.59

 distances

0.59

 Spacing

0.59

 Distance

0.57

gap

0.57

 cellspacing

0.56

 jarak

0.55

Activations Density 0.055%

terms related to spacing and distance measurements in a physical or technical context

distance and spacing

No Comments

No Known Activations