INDEX

Explanations

geographical locations

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

MLLoader

-0.81

aarrggbb

-0.78

脚注の使い方

-0.76

 AssemblyCompany

-0.74

 Rodin

-0.73

mappedBy

-0.73

 متعلقه

-0.68

 Mongolian

-0.66

 InputDecoration

-0.65

 Administrativna

-0.64

POSITIVE LOGITS

 Florida

1.33

Florida

1.20

 Broward

1.08

 FLORIDA

1.04

 Palm

0.96

 florida

0.95

 Everglades

0.93

florida

0.92

FLOR

0.91

 Miami

0.86

Activations Density 0.238%

geographical locations

No Comments

No Known Activations