INDEX

Explanations

image-related elements in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Pfa

-0.74

 EconPapers

-0.69

 Makoto

-0.68

 Healey

-0.68

ัฐ

-0.67

urop

-0.66

 Becher

-0.66

 Alvarez

-0.66

edel

-0.66

 Heine

-0.65

POSITIVE LOGITS

img

1.35

img

1.21

Img

1.06

Img

0.92

IMG

0.89

 imgs

0.88

imgs

0.83

 sumpay

0.80

Imgs

0.80

imgUrl

0.80

Activations Density 0.064%

image-related elements in the document

No Comments

No Known Activations