INDEX

Explanations

the letter "N" followed by numbers

oai_token-act-pair · gpt-3.5-turbo

mentions of the letter 'N' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 CLSID

-0.82

xual

-0.78

 breeze

-0.67

 highs

-0.65

 mushrooms

-0.64

 heights

-0.63

 acron

-0.62

 communism

-0.62

MODE

-0.62

 slic

-0.62

POSITIVE LOGITS

uggets

1.21

ihil

1.10

umerous

1.05

erves

1.05

urse

1.05

ominated

1.03

guyen

1.03

ucle

1.02

aughty

1.01

ested

1.00

Activations Density 0.024%

the letter "N" followed by numbers

mentions of the letter 'N' in various contexts

No Comments

No Known Activations