INDEX

Explanations

names of political figures and organizations

oai_token-act-pair · gpt-3.5-turbo

names of political figures and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Denver

-0.84

Philadelphia

-0.78

 Pittsburgh

-0.75

Miami

-0.74

 Luthor

-0.74

Newsletter

-0.73

Cub

-0.72

furt

-0.72

 Staten

-0.71

ARDIS

-0.70

POSITIVE LOGITS

 Sharma

1.23

 Singh

1.15

 Kumar

1.11

jriwal

1.06

bh

1.05

 Bhar

1.05

 Sabha

1.03

 Patel

1.01

umbai

0.99

Raj

0.99

Activations Density 0.347%

names of political figures and organizations

names of political figures and their affiliations

No Comments

No Known Activations