INDEX

Explanations

phrases related to agreement or consensus

oai_token-act-pair · gpt-3.5-turbo

references to consumption or consumers

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

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

WOOD

-0.78

 Meadow

-0.74

 horses

-0.70

 Pegasus

-0.66

 Peaks

-0.65

 Pharaoh

-0.64

 Refuge

-0.64

 Jehovah

-0.63

 Hoover

-0.63

 Wast

-0.62

POSITIVE LOGITS

ervatives

1.46

umers

1.36

ensus

1.34

cientious

1.33

piracy

1.32

ensual

1.31

ervative

1.28

idered

1.26

istent

1.23

cription

1.23

Activations Density 0.014%

phrases related to agreement or consensus

references to consumption or consumers

No Comments

No Known Activations