INDEX

Explanations

words related to medical professionals, particularly veterinarians and doctors

oai_token-act-pair · gpt-3.5-turbo

references to veterinary and medical professionals

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

 Flavoring

-0.95

uble

-0.81

 Territories

-0.75

 Strongh

-0.73

 Stronghold

-0.72

utenberg

-0.71

atan

-0.68

auri

-0.65

 Underworld

-0.63

 Dwar

-0.63

POSITIVE LOGITS

 examiner

1.08

 practitioner

1.02

 psychiatrist

0.99

 doctor

0.97

 physician

0.94

 clinic

0.93

 supervision

0.92

 diagnoses

0.92

autions

0.88

diagn

0.87

Activations Density 0.098%

words related to medical professionals, particularly veterinarians and doctors

references to veterinary and medical professionals

No Comments

No Known Activations