INDEX

Explanations

different variations of the word 'thumbnail'

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

image or video thumbnails

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

 isof

-0.49

Зноскі

-0.49

 setIs

-0.48

 okuyayım

-0.45

 Italijani

-0.43

 Gesetzes

-0.43

gdx

-0.42

 heisst

-0.42

 valsty

-0.41

әрмәләр

-0.41

POSITIVE LOGITS

thumbnail

2.44

 thumbnail

2.31

Thumbnail

2.14

 Thumbnail

2.13

 thumbnails

1.88

 Thumbnails

1.58

thumbnails

1.54

Thumb

1.37

thumb

1.24

 Thumb

1.16

Activations Density 0.003%

different variations of the word 'thumbnail'

image or video thumbnails

No Comments

No Known Activations