INDEX

Explanations

information related to vaccines and medical studies

oai_token-act-pair · gpt-3.5-turbo

references to vaccines and vaccination

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

ŃĶ

-0.83

agher

-0.75

erva

-0.74

rian

-0.70

notations

-0.69

tera

-0.69

hiba

-0.66

Ĥª

-0.66

Else

-0.66

 disorderly

-0.65

POSITIVE LOGITS

 vaccine

0.96

eers

0.93

 vaccines

0.89

 vaccinations

0.86

 vaccination

0.86

 Vacc

0.81

 immun

0.81

 vacc

0.79

cz

0.78

 inoc

0.78

Activations Density 0.016%

information related to vaccines and medical studies

references to vaccines and vaccination

No Comments

No Known Activations