INDEX

Explanations

Italian words or names

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the name "ello" and variations of people's names in the context of celebrity or notable figures

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

ãĥ¼ãĥĨ

-0.86

lopp

-0.69

PAX

-0.67

ciating

-0.65

ps

-0.64

IFA

-0.64

PER

-0.63

ERC

-0.63

Gil

-0.63

aur

-0.62

POSITIVE LOGITS

ello

0.71

iders

0.70

ousel

0.70

tarians

0.70

ucci

0.67

atted

0.65

annis

0.64

insky

0.64

ursed

0.64

 beans

0.63

Activations Density 0.025%

Italian words or names

the occurrences of the name "ello" and variations of people's names in the context of celebrity or notable figures

No Comments

No Known Activations