INDEX

Explanations

words related to medical institutions or healthcare settings

oai_token-act-pair · gpt-3.5-turbo

references to hospitals and hospital-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

lass

-0.79

yip

-0.75

pas

-0.71

ozy

-0.71

artisan

-0.70

 Helpful

-0.69

mire

-0.68

xual

-0.66

BOOK

-0.66

lyr

-0.65

POSITIVE LOGITS

ization

0.94

itals

0.94

 patients

0.94

 outpatient

0.89

NHS

0.88

 Patients

0.88

ised

0.87

ity

0.86

 patient

0.84

ilitating

0.84

Activations Density 0.048%

words related to medical institutions or healthcare settings

references to hospitals and hospital-related contexts

No Comments

No Known Activations