INDEX

Explanations

terms related to ethics and morality

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

morality

np_acts-logits-general · gemini-2.0-flash

moral character and implications

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

•moral_agent

No Comments

Negative Logits

 GenerationType

-0.59

<%=

-0.58

Sklici

-0.55

 FetchType

-0.54

="@+

-0.54

#+#

-0.53

ühungen

-0.52

 Reverso

-0.51

 Shuk

-0.49

 Lieb

-0.49

POSITIVE LOGITS

 moral

1.13

 Moral

1.05

moral

1.01

Moral

0.99

 morales

0.97

 morals

0.95

 morally

0.88

 morality

0.84

 ethics

0.80

 ethical

0.79

Activations Density 0.077%

terms related to ethics and morality

morality

moral character and implications

No Comments

No Known Activations