INDEX

Explanations

technical terms related to web development, specifically within the Django framework

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

Code snippets or file paths

np_acts-logits-general · gemini-2.0-flash

django imports and models

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

 betweenstory

-0.96

 незавершена

-0.87

 дописавши

-0.84

المناصب

-0.81

DockStyle

-0.78

onViewCreated

-0.78

EndInit

-0.77

цездатний

-0.77

principalColumn

-0.74

RectangleBorder

-0.73

POSITIVE LOGITS

 django

0.80

 Django

0.60

 Atlanta

0.57

DetailView

0.57

django

0.54

isnull

0.49

 Georgia

0.48

queryset

0.48

 South

0.46

Django

0.45

Activations Density 0.139%

technical terms related to web development, specifically within the Django framework

Code snippets or file paths

django imports and models

No Comments

No Known Activations