INDEX

Explanations

references to popular media franchises, particularly in relation to games and character names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ScopeManager

-0.66

GIVEREF

-0.64

 ioutil

-0.63

 CreateTagHelper

-0.62

OrBuilder

-0.61

 &___

-0.61

Gizmos

-0.61

 Pilate

-0.60

ändler

-0.60

 CarPlay

-0.60

POSITIVE LOGITS

 series

0.56

 franchise

0.48

 Series

0.47

シリーズ

0.44

系列

0.44

 című

0.44

series

0.43

 Hivatalos

0.43

weixin

0.43

 Voraus

0.42

Activations Density 0.133%

references to popular media franchises, particularly in relation to games and character names

No Comments

No Known Activations