INDEX

Explanations

sections of text separating the actual content as "Advertisements" or as unrelated text such as "

oai_token-act-pair · gpt-3.5-turbo

phrases related to advertisements or promotional 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

 Shades

-0.66

 naughty

-0.65

Tir

-0.64

asel

-0.64

 Stellar

-0.63

Hog

-0.62

 ambassadors

-0.62

½

-0.61

 Malk

-0.61

Ń·

-0.61

POSITIVE LOGITS

NPR

0.99

JUST

0.86

Bloomberg

0.83

Since

0.83

Likewise

0.81

Companies

0.80

Asked

0.80

Yet

0.79

Eventually

0.79

Security

0.79

Activations Density 0.033%

sections of text separating the actual content as "Advertisements" or as unrelated text such as "

phrases related to advertisements or promotional content

No Comments

No Known Activations