INDEX

Explanations

phrases indicating an intention or desire to do something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating intent or desire

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

furt

-0.72

 lying

-0.65

glers

-0.65

naires

-0.65

mob

-0.65

ById

-0.62

MpServer

-0.62

 lurking

-0.61

cuts

-0.61

 costing

-0.61

POSITIVE LOGITS

 thank

1.41

 reiterate

1.39

 clarify

1.36

 congratulate

1.35

 emphasize

1.35

 remind

1.31

 reassure

1.21

 THANK

1.20

 warn

1.17

 assure

1.16

Activations Density 0.111%

phrases indicating an intention or desire to do something

phrases indicating intent or desire

No Comments

No Known Activations