INDEX

Explanations

references to the Medicare program

oai_token-act-pair · gpt-3.5-turbo

mentions of Medicare and its associated contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

semble

-0.78

lang

-0.76

angers

-0.75

orically

-0.72

*/(

-0.72

urb

-0.72

 Noah

-0.69

orical

-0.68

acters

-0.66

ombs

-0.64

POSITIVE LOGITS

 beneficiaries

0.98

 Advantage

0.97

 Benefits

0.88

 reimbursement

0.88

 Medicare

0.88

 Payment

0.82

 entitle

0.81

 reimburse

0.79

 payroll

0.77

Care

0.77

Activations Density 0.013%

references to the Medicare program

mentions of Medicare and its associated contexts

No Comments

No Known Activations