INDEX

Explanations

references to images and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

UnusedPrivate

-1.02

@"/

-0.83

expandindo

-0.82

 >=",

-0.79

IsPostBack

-0.77

 "..\..\..\

-0.75

/>";

-0.74

 traditionnels

-0.74

 дописавши

-0.73

principalColumn

-0.70

POSITIVE LOGITS

 images

1.70

 image

1.51

 Images

1.50

 Image

1.48

 IMAGE

1.43

images

1.41

 getImage

1.39

Images

1.35

 IMAGES

1.34

IMAGE

1.33

Activations Density 0.059%

references to images and their variations

No Comments

No Known Activations