INDEX

Explanations

references to geographical or religious locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

}))

-0.82

ılıyor

-0.79

 pinulongan

-0.73

 Morty

-0.72

 Mukherjee

-0.69

fruta

-0.69

咙

-0.69

ilesh

-0.68

 Chiesa

-0.68

endu

-0.67

POSITIVE LOGITS

EAP

0.96

PAH

0.86

QApplication

0.85

CAI

0.82

 IMAP

0.81

 Esau

0.81

CharArray

0.81

 Wayback

0.80

GAP

0.80

 MainAxisSize

0.79

Activations Density 4.961%

references to geographical or religious locations

No Comments

No Known Activations