INDEX

Explanations

references to people being treated or taken to hospitals

oai_token-act-pair · gpt-3.5-turbo

references to hospitals and medical treatment following incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 monopol

-0.89

 monopoly

-0.79

wolves

-0.70

opp

-0.68

 rivals

-0.67

 imitate

-0.65

 hypoc

-0.65

 dominance

-0.65

 witches

-0.64

 dynasty

-0.64

POSITIVE LOGITS

rapnel

0.95

 paramedics

0.89

EMS

0.87

ysis

0.83

 medically

0.81

 custody

0.79

ambers

0.78

oulder

0.77

EMS

0.77

ospital

0.75

Activations Density 0.294%

references to people being treated or taken to hospitals

references to hospitals and medical treatment following incidents

No Comments

No Known Activations