INDEX

Explanations

numbers or quantities mentioned in relation to something else

oai_token-act-pair · gpt-3.5-turbo

the phrase "or" used in various contexts or quantifications

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

 Reporter

-0.73

ECH

-0.70

ires

-0.69

OTOS

-0.67

VERTISEMENT

-0.67

ADVERTISEMENT

-0.67

Monitor

-0.67

 VIDEOS

-0.65

 Pony

-0.63

Mech

-0.63

POSITIVE LOGITS

chard

1.20

ifice

1.20

acle

1.14

ific

1.11

nam

1.07

chid

1.05

lando

1.01

acular

0.99

thodox

0.98

acles

0.97

Activations Density 0.109%

numbers or quantities mentioned in relation to something else

the phrase "or" used in various contexts or quantifications

No Comments

No Known Activations