INDEX

Explanations

terms related to legal documents

oai_token-act-pair · gpt-3.5-turbo

key nouns and terms related to laws and regulations

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

veyard

-0.65

lease

-0.64

NetMessage

-0.64

ModLoader

-0.59

rav

-0.59

medi

-0.58

selves

-0.58

AHL

-0.56

arp

-0.56

CHAPTER

-0.56

POSITIVE LOGITS

 --------------------

0.80

eus

0.76

wana

0.66

 ----------------

0.65

oros

0.63

è¦ļéĨĴ

0.62

cair

0.60

 Makoto

0.60

BuyableInstoreAndOnline

0.60

 Boko

0.60

Activations Density 0.513%

terms related to legal documents

key nouns and terms related to laws and regulations

No Comments

No Known Activations