INDEX

Explanations

words ending with the letter 'n'

oai_token-act-pair · gpt-3.5-turbo

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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 slack

-0.62

 frank

-0.62

 compe

-0.62

Vaj

-0.60

 WRITE

-0.60

 welf

-0.59

 BALL

-0.58

Oracle

-0.56

 asleep

-0.56

 Remastered

-0.56

POSITIVE LOGITS

uggets

1.29

autical

1.27

ameless

1.27

ativity

1.24

imble

1.22

ectar

1.18

anny

1.14

ginx

1.14

atal

1.13

umerous

1.11

Activations Density 0.036%

words ending with the letter 'n'

the letter "n" in various contexts

No Comments

No Known Activations