INDEX

Explanations

code and references related to HTML and AngularJS templates

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

HTML attributes or class names

np_acts-logits-general · gemini-2.0-flash

web component attributes and templating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 تضيفلها

-0.75

 NSCoder

-0.71

indd

-0.65

bewerken

-0.65

tagHelperRunner

-0.63

 Roskov

-0.63

photobucket

-0.62

 lenker

-0.59

 ProtoMessage

-0.58

//

-0.57

POSITIVE LOGITS

 slot

0.67

Slot

0.54

rungsseite

0.53

slot

0.51

 SLOT

0.51

0.50

 slots

0.50

 Slot

0.49

 track

0.48

Activations Density 0.354%

code and references related to HTML and AngularJS templates

HTML attributes or class names

web component attributes and templating

No Comments

No Known Activations