INDEX

Explanations

phrases related to image selection and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ویکی‌پدیای

-0.58

lever

-0.56

 AssemblyVersion

-0.54

 MessageBoxIcon

-0.52

aringan

-0.52

unkel

-0.51

Према

-0.51

Fordítás

-0.50

 onAnimation

-0.50

 Uncategorized

-0.50

POSITIVE LOGITS

 ostavi

0.53

hoea

0.53

int

0.51

 EdgeInsets

0.50

ant

0.49

 يتيمه

0.49

site

0.48

jama

0.47

IME

0.46

Vidite

0.45

Activations Density 0.154%

phrases related to image selection and manipulation

No Comments

No Known Activations