INDEX

Explanations

references to image processing and decoding in programming contexts

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

loading images or decoding files

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

 createSlice

-0.66

 Infórmanos

-0.65

новниш

-0.63

IBarButtonItem

-0.62

IBAction

-0.61

 invokingState

-0.57

MigrationBuilder

-0.56

 Paglinawan

-0.52

 tslint

-0.51

cupertino

-0.50

POSITIVE LOGITS

picasso

0.51

ImageLoader

0.44

asset

0.33

ِّف

0.32

 tải

0.31

 images

0.30

image

0.30

errHandler

0.30

 image

0.29

hängen

0.29

Activations Density 0.007%

references to image processing and decoding in programming contexts

loading images or decoding files

No Comments

No Known Activations