INDEX

Explanations

names of individuals and titles of officials

oai_token-act-pair · gpt-3.5-turbo

prominent names or initials of individuals mentioned in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Rebels

-0.80

 Wonderland

-0.76

 Cerberus

-0.76

 Rebellion

-0.72

 womb

-0.70

 Leviathan

-0.67

 Pegasus

-0.65

 theaters

-0.65

 Firefly

-0.64

 dystop

-0.63

POSITIVE LOGITS

anya

1.08

ona

1.06

isha

1.04

ileen

1.00

ergus

0.98

leen

0.97

ilyn

0.95

ilda

0.95

lyss

0.95

ureen

0.95

Activations Density 0.257%

names of individuals and titles of officials

prominent names or initials of individuals mentioned in the document

No Comments

No Known Activations