INDEX

Explanations

cheese varieties, especially cheddar

oai_token-act-pair · gpt-3.5-turbo

food-related terms, particularly different types of cheese

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

YL

-0.69

writer

-0.67

onics

-0.66

 Paige

-0.66

pter

-0.63

WC

-0.62

Eck

-0.62

iating

-0.62

 persecut

-0.61

 Deng

-0.61

POSITIVE LOGITS

 Cheese

1.31

 cheese

1.23

clair

1.15

heddar

0.97

 chees

0.92

insula

0.83

asper

0.80

rontal

0.78

xon

0.77

 Angus

0.76

Activations Density 0.025%

cheese varieties, especially cheddar

food-related terms, particularly different types of cheese

No Comments

No Known Activations