INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

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

adr

-0.64

 DRAG

-0.63

 Maker

-0.62

ILA

-0.62

 FranÃ§

-0.62

 Barth

-0.61

andom

-0.60

Lost

-0.60

acs

-0.60

oglu

-0.60

POSITIVE LOGITS

ness

1.70

ly

1.51

nesses

1.50

est

1.31

NESS

1.15

itude

1.10

LY

1.03

 enough

0.99

ening

0.97

hearted

0.97

Activations Density 0.201%

proper nouns or names

No Comments

No Known Activations

proper nouns or names

No Comments

No Known Activations