INDEX

Explanations

medical terms and phrases related to diagnoses

oai_token-act-pair · gpt-3.5-turbo

terms related to diagnoses in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hire

-0.74

perty

-0.73

atility

-0.70

 dstg

-0.70

hester

-0.69

ouver

-0.66

ogle

-0.66

iety

-0.64

uble

-0.64

orthy

-0.63

POSITIVE LOGITS

ostics

1.21

ostic

1.14

 diagnoses

1.03

 Diagn

1.00

 diagnosis

0.98

osis

0.96

abetes

0.84

oses

0.83

agn

0.83

 diagn

0.81

Activations Density 0.030%

medical terms and phrases related to diagnoses

terms related to diagnoses in medical contexts

No Comments

No Known Activations