INDEX

Explanations

mentions of opioid-related terms

oai_token-act-pair · gpt-3.5-turbo

references to opioids and opioid-related issues

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

elong

-1.04

wagen

-0.83

Bird

-0.83

eor

-0.78

 Celest

-0.76

plane

-0.75

birds

-0.75

 Rapt

-0.74

planes

-0.73

ership

-0.72

POSITIVE LOGITS

 analges

1.30

 opioid

1.24

 overdose

1.21

 opioids

1.16

 fentanyl

1.14

 overdoses

1.03

 medication

1.01

 addiction

1.00

 drugs

1.00

 medications

0.98

Activations Density 0.014%

mentions of opioid-related terms

references to opioids and opioid-related issues

No Comments

No Known Activations