INDEX

Explanations

medical terms related to medications

oai_token-act-pair · gpt-3.5-turbo

references to prescribed medications and their implications

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

İ

-0.85

adia

-0.74

bread

-0.73

 Horn

-0.70

doors

-0.68

Wind

-0.67

 Democr

-0.67

 Literary

-0.67

izons

-0.66

bour

-0.65

POSITIVE LOGITS

 medication

1.24

 medications

1.23

 prescriptions

0.99

 overdose

0.99

 pills

0.97

 regimen

0.96

 dosage

0.94

 prescribing

0.92

 prescribed

0.92

 prescription

0.89

Activations Density 0.018%

medical terms related to medications

references to prescribed medications and their implications

No Comments

No Known Activations