INDEX

Explanations

references to locations or areas related to exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

ParallelGroup

-0.61

WithIOException

-0.54

 Adoption

-0.50

vestream

-0.49

XmlAccessType

-0.49

Посилання

-0.47

 Tyskland

-0.47

 Arquivado

-0.47

 adoption

-0.47

 nových

-0.47

POSITIVE LOGITS

 itinerary

0.71

 travellers

0.70

 traveler

0.67

 traveller

0.66

 travelers

0.65

 sightseeing

0.64

 souvenirs

0.63

 estimés

0.63

 tourist

0.63

 souvenir

0.59

Activations Density 0.174%

references to locations or areas related to exploration

No Comments

No Known Activations