INDEX

Explanations

references to mythical creatures, specifically dragons and monsters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ujednoznacz

-0.65

aliana

-0.64

hews

-0.63

misu

-0.60

脚注の使い方

-0.59

marginHorizontal

-0.58

meneu

-0.58

 jojo

-0.57

owels

-0.56

titleMargin

-0.56

POSITIVE LOGITS

 monster

1.21

monster

1.07

 dragon

1.06

 monstruo

1.03

 monsters

1.03

 beast

1.03

 creature

0.99

 bestia

0.93

 Dragon

0.93

 Monster

0.93

Activations Density 0.259%

references to mythical creatures, specifically dragons and monsters

No Comments

No Known Activations