INDEX

Explanations

different social media actions related to blocking and following users

oai_token-act-pair · gpt-3.5-turbo

phrases associated with social media interactions and user engagement

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

ueller

-0.76

 concoct

-0.75

renheit

-0.72

elfth

-0.70

 surviving

-0.69

intendent

-0.69

yre

-0.67

 butcher

-0.67

 champagne

-0.66

 quaint

-0.66

POSITIVE LOGITS

 Allows

1.12

 Emails

1.07

 Tweet

1.03

 Comments

0.98

 Password

0.95

 Shares

0.94

 Message

0.93

 Actions

0.92

 Posted

0.91

 Topic

0.91

Activations Density 0.057%

different social media actions related to blocking and following users

phrases associated with social media interactions and user engagement

No Comments

No Known Activations