INDEX

Explanations

references to footage and images used in media production

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

visual media clips

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

#+#

-0.63

reportWebVitals

-0.62

MigrationBuilder

-0.61

 jspb

-0.56

Personendaten

-0.54

tagext

-0.54

الحياه

-0.51

Cyfarwyddwr

-0.47

WriteTagHelper

-0.47

 Himo

-0.47

POSITIVE LOGITS

 collage

0.54

 images

0.51

 viejos

0.46

 disparate

0.44

getImage

0.44

 vintage

0.43

昔の

0.43

 görüntüleri

0.43

utebol

0.43

 clips

0.43

Activations Density 0.018%

references to footage and images used in media production

visual media clips

No Comments

No Known Activations