INDEX

Explanations

terms and concepts related to ethics and morality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stroke

-0.52

 inacces

-0.51

 excitedly

-0.51

 Haddad

-0.49

}),

-0.49

VH

-0.48

 Stedman

-0.48

舺

-0.48

Identyfik

-0.48

 definitive

-0.47

POSITIVE LOGITS

 moral

1.08

 Moral

1.06

Moral

0.99

 ethics

0.98

 ethical

0.97

 morals

0.96

moral

0.95

Ethics

0.93

 morality

0.93

 Ethics

0.91

Activations Density 0.348%

terms and concepts related to ethics and morality

No Comments

No Known Activations