INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

references to specific people, particularly those with the name "Nak" or similar variations

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

DVD

-0.69

 ILCS

-0.68

 sexes

-0.68

 grease

-0.66

 Warwick

-0.65

ORGE

-0.64

lav

-0.64

 butterflies

-0.63

 Hercules

-0.63

 opener

-0.63

POSITIVE LOGITS

amura

1.27

amoto

1.25

imura

1.11

ay

1.01

oda

0.99

iri

0.98

hod

0.96

aya

0.95

ril

0.95

ata

0.94

Activations Density 0.014%

people's names

references to specific people, particularly those with the name "Nak" or similar variations

No Comments

No Known Activations