INDEX

Explanations

mentions of cities and urban settings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 themſelves

-0.95

 Huguen

-0.81

 Infin

-0.80

 myſelf

-0.80

Билгалдахарш

-0.78

 Suprema

-0.77

 Saxons

-0.76

 mariée

-0.76

 persegu

-0.76

 Svensk

-0.73

POSITIVE LOGITS

 city

1.64

 cities

1.63

 City

1.61

 CITY

1.52

 Cities

1.48

cities

1.38

Cities

1.38

 getCity

1.35

city

1.30

City

1.29

Activations Density 0.053%

mentions of cities and urban settings

No Comments

No Known Activations