INDEX

Explanations

praise or compliments given to individuals or groups

oai_token-act-pair · gpt-3.5-turbo

instances of praise or commendation towards individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soDeliveryDate

-0.87

soever

-0.76

ogens

-0.75

gey

-0.74

 incompatible

-0.74

Default

-0.74

UME

-0.73

umes

-0.73

restricted

-0.72

 contradicts

-0.72

POSITIVE LOGITS

 accomplishments

1.39

 accomplishment

1.36

 bravery

1.34

 successes

1.29

 achievements

1.24

 ingenuity

1.22

 courage

1.21

 professionalism

1.19

 success

1.17

 achievement

1.14

Activations Density 0.411%

praise or compliments given to individuals or groups

instances of praise or commendation towards individuals or groups

No Comments

No Known Activations