INDEX

Explanations

mentions of governments or political entities

oai_token-act-pair · gpt-3.5-turbo

references to governments and political entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

»Ĵ

-0.84

ranging

-0.70

 Trafford

-0.67

near

-0.66

 Bian

-0.63

 Cham

-0.62

actionDate

-0.62

ixt

-0.60

rossover

-0.60

Tus

-0.59

POSITIVE LOGITS

 owes

1.43

 ought

1.34

 cannot

1.32

 deserves

1.31

 knows

1.27

 shouldn

1.25

 cares

1.21

 needs

1.20

 lacks

1.20

 understands

1.20

Activations Density 0.572%

mentions of governments or political entities

references to governments and political entities

No Comments

No Known Activations