INDEX

Explanations

words related to ethical concepts or discussions

oai_token-act-pair · gpt-3.5-turbo

references to ethics-related topics and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Clockwork

-0.78

Stock

-0.74

eworld

-0.72

enment

-0.72

 Eclipse

-0.71

upt

-0.70

âĢ¢âĢ¢âĢ¢âĢ¢

-0.70

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.68

nces

-0.68

nant

-0.67

POSITIVE LOGITS

onomic

0.93

 ethics

0.85

 waivers

0.81

 watchdog

0.80

 adviser

0.77

 lawyer

0.74

onom

0.74

 advisers

0.74

 disclosure

0.73

ilon

0.72

Activations Density 0.011%

words related to ethical concepts or discussions

references to ethics-related topics and discussions

No Comments

No Known Activations