INDEX

Explanations

geographic directional terms and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cref

-0.70

 fós

-0.67

 éte

-0.64

acam

-0.64

Personensuche

-0.63

 treno

-0.63

 Dover

-0.63

 Zamb

-0.62

Rath

-0.61

 LiveData

-0.58

POSITIVE LOGITS

HEAST

1.12

Southwest

1.01

 Southwest

1.00

southwest

0.97

Northeast

0.91

 southwest

0.90

heast

0.87

 northeast

0.86

NW

0.85

 Northeast

0.85

Activations Density 0.139%

geographic directional terms and their contexts

No Comments

No Known Activations