INDEX

Explanations

words related to healthcare and hospitals

oai_token-act-pair · gpt-3.5-turbo

mentions of hospitals

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

 Helpful

-0.85

lass

-0.76

yip

-0.75

tl

-0.75

BOOK

-0.70

xual

-0.70

oria

-0.69

ascript

-0.65

wcsstore

-0.65

ozy

-0.64

POSITIVE LOGITS

itals

0.94

 outpatient

0.80

opath

0.77

NHS

0.76

ization

0.75

 admissions

0.72

ilitating

0.72

aceutical

0.69

ospital

0.69

 cafeteria

0.69

Activations Density 0.022%

words related to healthcare and hospitals

mentions of hospitals

No Comments

No Known Activations