INDEX

Explanations

phrases related to recommendations and online purchasing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

άνι

-0.52

Conteúdo

-0.50

 mour

-0.48

roud

-0.47

 Cher

-0.46

asher

-0.45

+");

-0.45

IVIA

-0.45

disciplinar

-0.45

LOAT

-0.45

POSITIVE LOGITS

 purchase

0.86

:✨

0.82

 acceptance

0.78

 ACCEPT

0.78

 PURCHASE

0.75

 accept

0.74

 accepted

0.71

SourceChecksum

0.71

 accepting

0.70

SharedDtor

0.70

Activations Density 0.426%

phrases related to recommendations and online purchasing processes

No Comments

No Known Activations