INDEX

Explanations

terms related to shadows and shading in a graphical context

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

shadow, BoxShadow, shadows

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

="@+

-0.77

########.

-0.74

RTSC

-0.72

BeginContext

-0.66

SourceChecksum

-0.65

!*\

-0.63

 viewDidLoad

-0.63

 IBOutlet

-0.60

oneofs

-0.60

OrNil

-0.60

POSITIVE LOGITS

BoxShadow

1.41

boxShadow

1.04

shadow

1.01

 SHADOW

0.87

 shadow

0.85

Shadow

0.82

shadowColor

0.80

 shadows

0.76

shadows

0.76

shadowOffset

0.75

Activations Density 0.007%

terms related to shadows and shading in a graphical context

shadow, BoxShadow, shadows

No Comments

No Known Activations