INDEX

Explanations

references to components within a system or product

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

didSet

-0.89

sizeCache

-0.84

 giudi

-0.82

 HasFactory

-0.80

 referrerpolicy

-0.78

umato

-0.77

 PopupWindow

-0.77

NameInMap

-0.76

httphttps

-0.75

 <>",

-0.75

POSITIVE LOGITS

 components

1.76

 component

1.72

components

1.68

Component

1.65

 Component

1.65

component

1.61

 Components

1.58

 COMPONENT

1.54

Components

1.45

COMPONENT

1.37

Activations Density 0.028%

references to components within a system or product

No Comments

No Known Activations