INDEX

Explanations

keywords related to viruses

oai_token-act-pair · gpt-3.5-turbo

mentions of viruses

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

fman

-0.80

alty

-0.77

notations

-0.76

ezvous

-0.75

ndum

-0.71

cair

-0.71

anooga

-0.71

cknow

-0.71

ilts

-0.70

âķĲâķĲ

-0.70

POSITIVE LOGITS

irus

1.03

 infection

0.94

 infections

0.94

 outbreak

0.93

 virus

0.85

 viruses

0.84

 outbreaks

0.83

infect

0.82

 infect

0.79

 disease

0.78

Activations Density 0.024%

keywords related to viruses

mentions of viruses

No Comments

No Known Activations