INDEX

Explanations

phrases related to newsletters or subscriptions

oai_token-act-pair · gpt-3.5-turbo

repeated phrases related to viewing or accessing content

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

cest

-0.72

manship

-0.68

DN

-0.67

Ì¶

-0.67

anke

-0.66

iasco

-0.66

eros

-0.64

ufact

-0.61

angan

-0.59

byss

-0.59

POSITIVE LOGITS

âĶĢâĶĢâĶĢâĶĢ

0.62

ById

0.62

ideos

0.61

 alive

0.61

opot

0.61

 VIDEOS

0.60

arger

0.59

Privacy

0.58

 unfold

0.58

 empty

0.58

Activations Density 0.093%

phrases related to newsletters or subscriptions

repeated phrases related to viewing or accessing content

No Comments

No Known Activations