INDEX

Explanations

expressions of positive experiences or satisfaction with services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

出版年

-0.52

 conseguenze

-0.49

 ajudá

-0.47

 tergantung

-0.47

esModule

-0.47

GeneratedMessage

-0.46

urlencoded

-0.46

mphony

-0.45

INSEE

-0.45

richTextPanel

-0.45

POSITIVE LOGITS

 rare

1.10

 rarity

0.99

 unusual

0.90

 uncommon

0.86

 RARE

0.85

Rare

0.85

 propOrder

0.84

unusual

0.84

 Rare

0.82

 atypical

0.80

Activations Density 0.212%

expressions of positive experiences or satisfaction with services

No Comments

No Known Activations