INDEX

Explanations

mentions of drug-related terms

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to injury or self-harm

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

BOOK

-0.89

UAL

-0.85

manship

-0.76

\\\\\\\\

-0.76

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

soDeliveryDate

-0.73

hare

-0.72

DragonMagazine

-0.69

ãģ®éŃĶ

-0.68

AU

-0.68

POSITIVE LOGITS

inite

1.31

luence

1.22

rastructure

1.17

ractions

1.15

inity

1.12

licted

1.11

acet

1.08

amous

1.08

erno

1.07

raction

1.05

Activations Density 0.008%

mentions of drug-related terms

terms and phrases related to injury or self-harm

No Comments

No Known Activations