INDEX

Explanations

terms related to moral or ethical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

SourceChecksum

-0.85

 Garland

-0.80

 myſelf

-0.77

Czytaj

-0.77

 Jefus

-0.77

 purpoſe

-0.76

 themſelves

-0.76

 cdti

-0.74

 itſelf

-0.74

 Sputnik

-0.72

POSITIVE LOGITS

 moral

1.12

 ethical

0.91

 ethics

0.87

moral

0.86

 Moral

0.85

 Ethics

0.83

 morality

0.81

Moral

0.81

 Ethical

0.70

Ethics

0.69

Activations Density 0.042%

terms related to moral or ethical concepts

No Comments

No Known Activations