INDEX

Explanations

words related to infections, diseases, and medical conditions

oai_token-act-pair · gpt-3.5-turbo

mentions of infections and related medical conditions

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

ibur

-0.87

*/(

-0.83

pload

-0.80

kee

-0.70

objects

-0.69

MER

-0.68

uchin

-0.67

ple

-0.67

¶æ

-0.67

ussian

-0.67

POSITIVE LOGITS

 infections

1.01

 infection

1.00

 infect

0.88

 Infect

0.87

 bacteria

0.87

 spores

0.86

 outbreak

0.86

 inoc

0.85

 infected

0.85

 outbreaks

0.85

Activations Density 0.013%

words related to infections, diseases, and medical conditions

mentions of infections and related medical conditions

No Comments

No Known Activations