INDEX

Explanations

medical facilities or centers

oai_token-act-pair · gpt-3.5-turbo

references to medical facilities and examinations

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

yip

-0.83

 newsp

-0.79

 Strongh

-0.78

wit

-0.78

urat

-0.75

isSpecialOrderable

-0.71

alist

-0.71

inous

-0.70

itiveness

-0.69

 iPod

-0.69

POSITIVE LOGITS

 Canaver

1.09

 Doctors

1.00

 Veter

0.99

 Medical

0.97

 medical

0.97

 doctors

0.96

 paramed

0.95

 physicians

0.95

 doctor

0.94

 nurses

0.94

Activations Density 0.220%

medical facilities or centers

references to medical facilities and examinations

No Comments

No Known Activations