INDEX

Explanations

key terms related to ethics

oai_token-act-pair · gpt-3.5-turbo

references to ethical standards and obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hof

-0.89

jong

-0.86

down

-0.86

lling

-0.82

peak

-0.78

coat

-0.77

gow

-0.74

xual

-0.74

pel

-0.74

ching

-0.72

POSITIVE LOGITS

ethical

1.14

 ethical

1.06

 ethics

0.99

onomic

0.94

 dile

0.91

 conscience

0.86

 disclosure

0.81

 considerations

0.78

 minded

0.78

 violations

0.76

Activations Density 0.010%

key terms related to ethics

references to ethical standards and obligations

No Comments

No Known Activations