INDEX

Explanations

elements related to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paglinawan

-0.75

 Picchu

-0.70

ukone

-0.65

tvguidetime

-0.63

verwijspagina

-0.63

onViewCreated

-0.59

 Мексичка

-0.59

 composizione

-0.57

Билгалдахарш

-0.57

MemoryWarning

-0.57

POSITIVE LOGITS

 restaurant

1.52

 restaurants

1.32

 cafe

1.28

 eatery

1.27

 Restaurant

1.18

restaurant

1.17

 café

1.17

 Cafe

1.13

 restaurante

1.13

Restaurant

1.09

Activations Density 0.186%

elements related to food and dining experiences

No Comments

No Known Activations