INDEX

Explanations

references to image loading and manipulation in programming

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

image processing code

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

:✨

-0.63

 EconPapers

-0.54

reportWebVitals

-0.50

+:+

-0.48

AddTagHelper

-0.48

]")]

-0.47

extAlignment

-0.46

 typelib

-0.44

AnimationsModule

-0.40

 autorytatywna

-0.40

POSITIVE LOGITS

BitmapFactory

0.58

ImageIO

0.56

fjspx

0.52

pexpr

0.51

 imageNamed

0.50

UIImage

0.48

NSData

0.47

BufferedImage

0.45

 perforated

0.45

 getImage

0.44

Activations Density 0.014%

references to image loading and manipulation in programming

image processing code

No Comments

No Known Activations