INDEX

Explanations

references to images and image-related actions

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

image searches and uploads

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

MigrationBuilder

-0.47

 creencias

-0.36

 maquin

-0.36

 stanu

-0.35

 środow

-0.34

écrivain

-0.34

 mecán

-0.32

 Glaube

-0.32

 actuaciones

-0.32

 kancel

-0.32

POSITIVE LOGITS

 uploads

0.83

 images

0.81

 uploading

0.78

 Images

0.77

 uploaded

0.76

 upload

0.75

 JPEG

0.73

 gallery

0.70

Img

0.70

 pictures

0.69

Activations Density 0.057%

references to images and image-related actions

image searches and uploads

No Comments

No Known Activations

references to images and image-related actions

image searches and uploads

No Comments

No Known Activations