INDEX

Explanations

references to pricing and value assessments in consumer reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

كويكب

-0.56

Hie

-0.54

ніципалі

-0.53

 poffible

-0.52

abancı

-0.52

uxxxx

-0.52

fatalError

-0.51

 CreateTagHelper

-0.51

 esternos

-0.50

 myſelf

-0.50

POSITIVE LOGITS

 promised

0.63

 bargain

0.62

 argint

0.59

 justify

0.58

 price

0.57

納得

0.57

Портал

0.57

enumi

0.55

 fair

0.54

fromCharCode

0.53

Activations Density 0.192%

references to pricing and value assessments in consumer reviews

No Comments

No Known Activations