INDEX

Explanations

references to geographical locations in the Northern Hemisphere

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

sstream

-0.92

 Krakowie

-0.85

 Pacer

-0.80

enumi

-0.79

%">

-0.78

 ToString

-0.76

 Lugano

-0.76

TestingModule

-0.76

IsPostBack

-0.75

Geplaatst

-0.74

POSITIVE LOGITS

north

1.50

 North

1.49

 north

1.37

North

1.36

 NORTH

1.36

NORTH

1.35

 Noth

1.13

 Nort

1.10

 Noord

0.93

 norte

0.92

Activations Density 0.061%

references to geographical locations in the Northern Hemisphere

No Comments

No Known Activations