INDEX

Explanations

mentions related to insurance

oai_token-act-pair · gpt-3.5-turbo

references to insurance and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

auri

-0.81

leon

-0.78

urb

-0.76

anism

-0.76

anie

-0.74

lins

-0.73

isha

-0.73

ebook

-0.73

dain

-0.73

ruciating

-0.72

POSITIVE LOGITS

 premiums

1.26

 broker

1.09

 issuer

1.07

 insurance

1.01

 brokerage

1.01

 companies

1.00

 reimbursement

0.98

 brokers

0.98

 carriers

0.95

 reimburse

0.95

Activations Density 0.039%

mentions related to insurance

references to insurance and related terms

No Comments

No Known Activations