INDEX

Explanations

mentions of the drug "meth" or "methamphetamine."

oai_token-act-pair · gpt-3.5-turbo

terms related to methamphetamine and its derivatives

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

DragonMagazine

-0.82

 Dull

-0.76

 Wolves

-0.75

Accessory

-0.73

Reviewer

-0.72

velength

-0.72

ç·

-0.70

 Vector

-0.70

 Ashe

-0.69

ORED

-0.67

POSITIVE LOGITS

 meth

1.18

amphetamine

1.15

ilit

1.03

oxy

1.02

 methamphetamine

0.95

hetamine

0.92

inks

0.91

oglobin

0.84

imes

0.82

 cocaine

0.81

Activations Density 0.012%

mentions of the drug "meth" or "methamphetamine."

terms related to methamphetamine and its derivatives

No Comments

No Known Activations