INDEX

Explanations

elements related to photography and group images

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

photographs and pictures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ChildScrollView

-0.43

 verfol

-0.41

 Bürgermeister

-0.39

 verfolgen

-0.36

 verfolgt

-0.35

 chase

-0.32

 witness

-0.32

hisattva

-0.32

 coronel

-0.30

뀔

-0.30

POSITIVE LOGITS

 photograph

0.75

 defaultstate

0.74

 photo

0.72

 Administrativna

0.71

 Photo

0.67

 Photos

0.66

photo

0.66

 photographs

0.65

 Photograph

0.65

 photos

0.64

Activations Density 0.103%

elements related to photography and group images

photographs and pictures

No Comments

No Known Activations