INDEX

Explanations

CSS and design-related properties

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

Code snippets and markup

np_acts-logits-general · gemini-2.0-flash

colors and archaic spellings

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

AddTagHelper

-0.52

binant

-0.52

 ModelExpression

-0.48

BeginInit

-0.48

ellery

-0.47

?}",

-0.47

<>

-0.47

":"+

-0.47

 }}"></

-0.46

makeConstraints

-0.45

POSITIVE LOGITS

 foncé

0.80

 lighten

0.77

 myſelf

0.76

 Cæsar

0.76

 Shakspeare

0.75

 itſelf

0.73

 betweenstory

0.72

 ſmall

0.72

 accents

0.70

 lighter

0.68

Activations Density 0.063%

CSS and design-related properties

Code snippets and markup

colors and archaic spellings

No Comments

No Known Activations