INDEX

Explanations

hashtags

oai_token-act-pair · gpt-3.5-turbo

hashtags

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oun

-0.84

 Gors

-0.79

 destro

-0.75

 slips

-0.75

 Ambrose

-0.73

 Sylv

-0.67

 commissions

-0.67

 cler

-0.66

 Deng

-0.66

Vie

-0.65

POSITIVE LOGITS

DIV

1.19

define

1.06

Gamer

1.03

################################

1.03

DonaldTrump

1.02

RIP

1.00

!/

0.99

Ask

0.99

MAG

0.97

Fake

0.95

Activations Density 0.019%

hashtags

hashtags

No Comments

No Known Activations