INDEX

Explanations

mention of potential risks and negative impacts on various aspects like health, economy, environment, and public safety

oai_token-act-pair · gpt-3.5-turbo

references to health and safety risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

zag

-0.64

DragonMagazine

-0.63

irection

-0.60

OUP

-0.60

 caveats

-0.59

OHN

-0.58

 greet

-0.57

udicrous

-0.56

gom

-0.55

hang

-0.55

POSITIVE LOGITS

 adversely

1.01

 livelihood

0.99

 morale

0.98

 negatively

0.97

 psyche

0.94

 downstream

0.89

 wellbeing

0.89

 stability

0.84

 financially

0.83

 competitiveness

0.82

Activations Density 0.352%

mention of potential risks and negative impacts on various aspects like health, economy, environment, and public safety

references to health and safety risks

No Comments

No Known Activations