INDEX

Explanations

questions starting with "Do" or "Do you"

oai_token-act-pair · gpt-3.5-turbo

direct questions or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

workshop

-0.72

ItemTracker

-0.69

swick

-0.67

DOC

-0.64

 Suite

-0.63

isu

-0.63

CVE

-0.60

ãĤ¼ãĤ¦ãĤ¹

-0.60

EStreamFrame

-0.60

uyomi

-0.59

POSITIVE LOGITS

zens

1.39

omsday

1.23

ctors

1.23

ctr

1.19

ppel

1.17

gging

1.14

herty

1.06

oley

1.03

ÄŁ

0.99

oming

0.98

Activations Density 0.043%

questions starting with "Do" or "Do you"

direct questions or inquiries

No Comments

No Known Activations