INDEX

Explanations

references to locations, specifically towns and communities

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

 Réponses

-0.74

 Karlsruhe

-0.73

setMsg

-0.73

Kira

-0.71

 MediatR

-0.69

 Warszawie

-0.69

 Blätter

-0.69

aviar

-0.68

 Samos

-0.67

λλ

-0.66

POSITIVE LOGITS

 town

1.53

 towns

1.46

 Town

1.39

 TOWN

1.36

Towns

1.32

Town

1.31

town

1.31

 Towns

1.28

towns

1.22

 Towne

1.22

Activations Density 0.043%

references to locations, specifically towns and communities

No Comments

No Known Activations