INDEX

Explanations

special characters and formatting indicators in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Filmografia

-0.47

 oculta

-0.41

 zapatos

-0.40

 separado

-0.40

 revelar

-0.39

 ocultar

-0.39

 minore

-0.38

 vulga

-0.37

 ไทย

-0.37

 Ziegler

-0.37

POSITIVE LOGITS

Tikang

0.77

RegistryLite

0.72

IMPORTED

0.70

 otomatig

0.69

 itſelf

0.68

Autoritní

0.66

 betweenstory

0.66

webElementXpaths

0.64

uxxxx

0.64

ſelves

0.63

Activations Density 0.703%

special characters and formatting indicators in the text

No Comments

No Known Activations