INDEX

Explanations

noten-ly indexed items such as lists or structured data points that may relate to clinical or observational studies and their perceived demographics

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

]]]

-0.64

contentLoaded

-0.58

InputTagHelper

-0.58

 Sarmiento

-0.57

Personensuche

-0.55

 greenish

-0.54

endent

-0.54

IsContent

-0.52

addComponent

-0.52

ญิง

-0.52

POSITIVE LOGITS

 UIAlert

0.57

 MaterialApp

0.56

 therefore

0.53

DotNetBar

0.53

esModule

0.52

 AppCompatTheme

0.51

RTHOOK

0.47

 Italijani

0.45

 PeEnEo

0.45

therefore

0.44

Activations Density 0.397%

noten-ly indexed items such as lists or structured data points that may relate to clinical or observational studies and their perceived demographics

No Comments

No Known Activations