INDEX

Explanations

words related to disabilities

oai_token-act-pair · gpt-3.5-turbo

terms related to disabilities and impairments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.69

advertising

-0.68

 profitability

-0.64

Sund

-0.64

Karl

-0.63

externalActionCode

-0.63

MER

-0.61

Companies

-0.61

hunt

-0.61

Transaction

-0.61

POSITIVE LOGITS

 disabilities

0.95

 autistic

0.91

 learners

0.83

 youths

0.83

Dys

0.82

obic

0.81

 disabled

0.81

 arthritis

0.80

 impaired

0.80

 inval

0.79

Activations Density 0.088%

words related to disabilities

terms related to disabilities and impairments

No Comments

No Known Activations