INDEX

Explanations

descriptions of characters or figures in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

setVerticalGroup

-0.57

enterOuterAlt

-0.51

ModelSerializer

-0.49

 kasarigan

-0.49

Literatuur

-0.48

 plantillas

-0.47

 parachoque

-0.47

 perfekte

-0.47

 perfecta

-0.46

 perfecte

-0.46

POSITIVE LOGITS

 woman

0.54

guy

0.54

 lady

0.51

man

0.48

 metal

0.46

 resembling

0.44

 gentleman

0.44

incón

0.44

 bureau

0.43

leb

0.43

Activations Density 0.591%

descriptions of characters or figures in narratives

No Comments

No Known Activations