INDEX

Explanations

references to the Dutch and related geographic or cultural terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Externé

-0.68

GEBURTSDATUM

-0.65

 صوتيه

-0.65

//

-0.59

 gevo

-0.58

 Fiona

-0.58

 Magno

-0.57

 Macle

-0.57

 Tunisian

-0.57

 Winchester

-0.57

POSITIVE LOGITS

 Dutch

3.21

Dutch

2.95

 Netherlands

2.79

 dutch

2.76

dutch

2.38

 Holland

2.38

Netherlands

2.34

 Dutchman

2.24

 Amsterdam

2.13

Holland

2.12

Activations Density 0.085%

references to the Dutch and related geographic or cultural terms

No Comments

No Known Activations