INDEX

Explanations

mentions of specific locations or events

oai_token-act-pair · gpt-3.5-turbo

phrases related to specific locations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Tsarnaev

-0.51

 Canaver

-0.50

 Glacier

-0.46

 Jacobs

-0.44

 Rubin

-0.44

 Kislyak

-0.44

 Musk

-0.44

etheless

-0.42

 Kaplan

-0.42

 Rudolph

-0.42

POSITIVE LOGITS

=-=-

0.65

iple

0.51

[|

0.49

ÃĥÃĤ

0.48

jri

0.45

 livest

0.44

omach

0.44

ayn

0.44

=]

0.43

Ü

0.42

Activations Density 3.973%

mentions of specific locations or events

phrases related to specific locations or events

No Comments

No Known Activations