INDEX

Explanations

details related to user profiles and their posts

oai_token-act-pair · gpt-3.5-turbo

references to user post counts and engagement metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Bhar

-0.80

ãĥ¼ãĤ¯

-0.72

bage

-0.72

 Horowitz

-0.67

inant

-0.66

rous

-0.66

itably

-0.65

otten

-0.64

bet

-0.63

SpaceEngineers

-0.63

POSITIVE LOGITS

 Posts

1.22

 Joined

0.95

Posts

0.88

ertodd

0.88

reply

0.77

 Highlands

0.72

 Rated

0.71

 Quote

0.70

pedia

0.70

 posts

0.70

Activations Density 0.013%

details related to user profiles and their posts

references to user post counts and engagement metrics

No Comments

No Known Activations