INDEX

Explanations

words related to diseases and medical terms

oai_token-act-pair · gpt-3.5-turbo

words and terms related to medical conditions, particularly infectious diseases

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

ELS

-0.85

ured

-0.64

URI

-0.63

 Strauss

-0.61

 Lomb

-0.60

bis

-0.59

 Chao

-0.59

elson

-0.59

 Petraeus

-0.57

 Peel

-0.56

POSITIVE LOGITS

apy

1.36

swer

1.07

idge

1.05

netic

0.99

apist

0.99

ther

0.98

nian

0.96

ington

0.90

mal

0.90

soever

0.89

Activations Density 0.010%

words related to diseases and medical terms

words and terms related to medical conditions, particularly infectious diseases

No Comments

No Known Activations