INDEX

Explanations

references to a specific fictional or gaming universe, possibly related to a brand

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Or" followed by variations or names associated with it

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

BILITIES

-0.71

ptoms

-0.69

INESS

-0.67

ãĤ¼ãĤ¦ãĤ¹

-0.65

 VIDEOS

-0.65

enment

-0.62

uristic

-0.62

eers

-0.60

FFER

-0.60

perature

-0.60

POSITIVE LOGITS

phans

1.27

chid

1.23

thodox

1.21

lando

1.20

phan

1.18

leans

1.18

chard

1.16

Else

1.10

pheus

1.10

acles

1.06

Activations Density 0.023%

references to a specific fictional or gaming universe, possibly related to a brand

mentions of the word "Or" followed by variations or names associated with it

No Comments

No Known Activations