INDEX

Explanations

references to opioid-related terms and information

oai_token-act-pair · gpt-3.5-turbo

terms related to opioids and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

elong

-1.00

semble

-0.86

ouf

-0.86

eor

-0.82

acular

-0.77

ateur

-0.76

aan

-0.76

tle

-0.73

 Lego

-0.72

rons

-0.70

POSITIVE LOGITS

 fentanyl

1.38

 opioid

1.36

 overdose

1.34

 analges

1.30

 overdoses

1.29

 morphine

1.20

 heroin

1.17

 opioids

1.16

 narc

1.15

 addiction

1.15

Activations Density 0.038%

references to opioid-related terms and information

terms related to opioids and their consequences

No Comments

No Known Activations