INDEX

Explanations

references to alignment and positioning in layouts or designs

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

HTML "align" attribute

np_acts-logits-general · gemini-2.0-flash

text alignment attributes

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

Jeografia

-0.84

 ModelExpression

-0.75

 Involvement

-0.70

geslacht

-0.68

 Réponses

-0.68

 يتيمه

-0.67

 involved

-0.66

 виправивши

-0.65

 ThemeData

-0.65

rawDesc

-0.65

POSITIVE LOGITS

 ALIGN

0.79

 Align

0.71

align

0.69

 Alig

0.64

Aligned

0.62

 alig

0.62

Align

0.60

 pins

0.59

 aligns

0.59

 align

0.58

Activations Density 0.177%

references to alignment and positioning in layouts or designs

HTML "align" attribute

text alignment attributes

No Comments

No Known Activations