INDEX

Explanations

references to specific restaurants and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Normdatei

-0.65

 useAuth

-0.62

 écou

-0.58

KommentareTeilen

-0.57

KEYCODE

-0.57

éraires

-0.56

 judíos

-0.55

льевич

-0.54

ziak

-0.54

 město

-0.53

POSITIVE LOGITS

 Grill

0.63

 restaurant

0.58

 Restaurant

0.55

 grill

0.54

 Hotel

0.53

LookAnd

0.49

 Tavern

0.49

insegna

0.48

Restaurant

0.48

 Oster

0.48

Activations Density 0.143%

references to specific restaurants and their characteristics

No Comments

No Known Activations