INDEX

Explanations

terms related to hazards and safety assessments

oai_token-act-pair · gpt-3.5-turbo

terms related to hazards 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gdala

-0.83

ombo

-0.83

oaded

-0.81

rams

-0.80

angelo

-0.73

ebus

-0.72

ulet

-0.72

ampires

-0.71

hetti

-0.71

HCR

-0.71

POSITIVE LOGITS

 hazard

1.07

 hazards

1.01

 Hazard

0.94

ously

0.87

azard

0.76

 mitigation

0.74

 hazardous

0.72

tnc

0.72

 advis

0.72

hooting

0.70

Activations Density 0.052%

terms related to hazards and safety assessments

terms related to hazards and safety risks

No Comments

No Known Activations