INDEX

Explanations

words related to healthcare programs, particularly Medicaid

oai_token-act-pair · gpt-3.5-turbo

references to Medicaid and related healthcare programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

semble

-0.89

cold

-0.78

lihood

-0.74

terday

-0.72

lass

-0.71

iple

-0.70

ibel

-0.70

ths

-0.69

hua

-0.68

wart

-0.66

POSITIVE LOGITS

 eligibility

1.03

 reimbursement

1.02

 reimburse

0.98

 recipients

0.96

 beneficiaries

0.95

 Medicaid

0.89

 expansion

0.88

 Expansion

0.88

 Benefits

0.82

 enrollment

0.81

Activations Density 0.028%

words related to healthcare programs, particularly Medicaid

references to Medicaid and related healthcare programs

No Comments

No Known Activations