INDEX

Explanations

phrases related to persuasion and manipulation

oai_token-act-pair · gpt-3.5-turbo

phrases related to manipulation and persuasion

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

wcsstore

-0.91

halla

-0.77

[+

-0.76

Ļ½

-0.75

iHUD

-0.72

VERTISEMENT

-0.69

FactoryReloaded

-0.69

EStream

-0.69

inventoryQuantity

-0.68

ãĤ´ãĥ³

-0.67

POSITIVE LOGITS

 consumers

1.48

 viewers

1.48

us

1.46

 audiences

1.46

 readers

1.42

 listeners

1.41

 Americans

1.40

 citizens

1.35

 attendees

1.33

 unsuspecting

1.31

Activations Density 0.520%

phrases related to persuasion and manipulation

phrases related to manipulation and persuasion

No Comments

No Known Activations