INDEX

Explanations

references to drive-throughs and drive-up services in relation to fast food establishments

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

-0.69

verwijspagina

-0.67

yntaxException

-0.66

 Вікі

-0.56

 terr

-0.52

rungsseite

-0.52

خار

-0.52

iseite

-0.51

 Alembic

-0.50

 sherry

-0.49

POSITIVE LOGITS

 McDonald

1.23

 McDonalds

1.17

 burger

1.16

McDonald

1.13

 burgers

1.06

 Burger

1.03

 franchise

0.99

Burger

0.99

 hamburger

0.96

 hamburgers

0.95

Activations Density 0.159%

references to drive-throughs and drive-up services in relation to fast food establishments

No Comments

No Known Activations