INDEX

Explanations

phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

quotation marks and potential speech or dialogue within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 adjud

-0.72

 administr

-0.72

 challeng

-0.68

 outsourcing

-0.68

bda

-0.62

hub

-0.62

 assigning

-0.62

 aggreg

-0.61

uton

-0.60

DP

-0.60

POSITIVE LOGITS

BuyableInstoreAndOnline

1.17

 largeDownload

0.99

Faith

0.88

We

0.87

":"/

0.87

Islam

0.86

Hey

0.83

Vers

0.81

Justice

0.80

Our

0.80

Activations Density 0.083%

phrases enclosed in quotation marks

quotation marks and potential speech or dialogue within the text

No Comments

No Known Activations