INDEX

Explanations

phrases related to medical conditions or treatments, specifically focusing on the word "patients."

oai_token-act-pair · gpt-3.5-turbo

references to patients in a medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

GGGG

-0.74

ģ«

-0.74

angular

-0.71

ãĥ¼ãĥĨãĤ£

-0.68

SourceFile

-0.67

sg

-0.65

region

-0.64

OPA

-0.64

shell

-0.64

å°Ĩ

-0.62

POSITIVE LOGITS

 patients

0.99

ients

0.95

 diagnosed

0.88

 Patients

0.88

 hospitalized

0.79

 patient

0.77

 confidentiality

0.76

ubs

0.74

iology

0.73

 smugglers

0.73

Activations Density 0.016%

phrases related to medical conditions or treatments, specifically focusing on the word "patients."

references to patients in a medical context

No Comments

No Known Activations