INDEX

Explanations

references to photography and visual imagery

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

about taking or looking at pictures

np_acts-logits-general · gemini-2.0-flash

photo, picture, and pose

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 verfol

-0.46

 verfolgen

-0.45

ChildScrollView

-0.43

 verfolgt

-0.41

Lähteet

-0.39

 écou

-0.37

 Bürgermeister

-0.37

 createState

-0.36

uition

-0.35

 mulighed

-0.35

POSITIVE LOGITS

 defaultstate

0.66

 photo

0.65

 selfies

0.64

 Selfie

0.64

 selfie

0.63

 photograph

0.61

合影

0.57

photo

0.57

 portrait

0.56

 poses

0.56

Activations Density 0.184%

references to photography and visual imagery

about taking or looking at pictures

photo, picture, and pose

No Comments

No Known Activations