INDEX

Explanations

terms related to health insurance and medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to insurance and healthcare status

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

resent

-0.81

ascript

-0.78

orously

-0.75

apult

-0.75

azaki

-0.74

ãĥķãĤ©

-0.71

Parser

-0.70

quickShipAvailable

-0.70

doi

-0.70

rawdownloadcloneembedreportprint

-0.70

POSITIVE LOGITS

 persons

1.19

 individuals

1.16

ness

1.07

 youths

1.02

 Persons

0.99

NESS

0.97

 households

0.97

 people

0.89

 Individuals

0.87

 adults

0.86

Activations Density 0.282%

terms related to health insurance and medical conditions

terms related to insurance and healthcare status

No Comments

No Known Activations