INDEX

Explanations

doctors or medical professionals

oai_token-act-pair · gpt-3.5-turbo

references to medical professionals, specifically doctors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Territories

-0.90

 Flavoring

-0.75

ptions

-0.67

uble

-0.65

âĸ¬

-0.64

CHAT

-0.62

regate

-0.60

 Liberation

-0.59

plings

-0.59

via

-0.58

POSITIVE LOGITS

 doctor

1.01

 prescribing

0.93

doctor

0.93

 examiner

0.88

 physician

0.86

 specializing

0.85

 practitioner

0.84

 doctors

0.83

 treating

0.83

 care

0.80

Activations Density 0.023%

doctors or medical professionals

references to medical professionals, specifically doctors

No Comments

No Known Activations