INDEX

Explanations

words related to hazards or hazards themselves

oai_token-act-pair · gpt-3.5-turbo

references to hazards and hazardous materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

gdala

-0.96

itton

-0.92

hetti

-0.88

ampires

-0.87

AIN

-0.84

inyl

-0.83

ombo

-0.80

orative

-0.79

oaded

-0.78

thood

-0.77

POSITIVE LOGITS

 hazards

0.94

 hazard

0.92

ously

0.88

 mitigation

0.73

 Patrol

0.73

 Hazard

0.72

hooting

0.71

SEE

0.70

 evacuation

0.69

 Bunny

0.67

Activations Density 0.043%

words related to hazards or hazards themselves

references to hazards and hazardous materials

No Comments

No Known Activations