INDEX

Explanations

names related to legal or political figures

oai_token-act-pair · gpt-3.5-turbo

names or titles of individuals and entities

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

ghai

-0.76

Orb

-0.63

 Geek

-0.62

etsk

-0.61

alys

-0.60

olulu

-0.60

orthern

-0.59

acity

-0.59

gate

-0.58

unct

-0.58

POSITIVE LOGITS

WOOD

1.49

BALL

1.48

VILLE

1.46

FIL

1.45

 EDITION

1.44

URA

1.44

SON

1.41

MAN

1.41

WOR

1.39

HEAD

1.39

Activations Density 0.292%

names related to legal or political figures

names or titles of individuals and entities

No Comments

No Known Activations