INDEX

Explanations

references to image processing and manipulation

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

image data or bitmap

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

aunt

-0.45

 Oster

-0.43

LoggerFactory

-0.40

 kesin

-0.40

reek

-0.40

pace

-0.40

 Feier

-0.39

 encant

-0.39

 ステン

-0.39

 Mood

-0.39

POSITIVE LOGITS

Bitmap

0.99

 Bitmap

0.80

 BitmapFactory

0.66

BitmapFactory

0.59

Personendaten

0.59

setImageBitmap

0.53

UIImage

0.53

 UIImage

0.48

 فريبيس

0.47

 Wikimedijinoj

0.47

Activations Density 0.001%

references to image processing and manipulation

image data or bitmap

No Comments

No Known Activations