INDEX

Explanations

phrases that introduce or emphasize a list of items or concepts

oai_token-act-pair · gpt-3.5-turbo

references to various subjects and topics denoted by "the" followed by descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SOM

-0.75

ANE

-0.67

ahn

-0.65

 Reincarn

-0.64

fulness

-0.63

 anew

-0.62

 Tsukuyomi

-0.62

 Chapel

-0.62

bye

-0.60

 Archdemon

-0.60

POSITIVE LOGITS

okÃ©

0.74

phabet

0.74

iler

0.70

oples

0.70

acan

0.68

erville

0.68

ilic

0.67

upper

0.67

eligible

0.67

visual

0.66

Activations Density 0.097%

phrases that introduce or emphasize a list of items or concepts

references to various subjects and topics denoted by "the" followed by descriptors

No Comments

No Known Activations