INDEX

Explanations

words or phrases related to the letter "n" followed by a specific word

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'n' within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 compe

-0.66

Ĥİ

-0.65

 horizont

-0.61

gerald

-0.61

å§«

-0.61

 Thumbnails

-0.59

 unsupported

-0.58

Vaj

-0.58

 Remastered

-0.57

 contacting

-0.57

POSITIVE LOGITS

uggets

1.22

igg

1.21

imble

1.18

anny

1.15

autical

1.13

uke

1.12

ought

1.10

umpy

1.10

igger

1.10

igh

1.09

Activations Density 0.028%

words or phrases related to the letter "n" followed by a specific word

occurrences of the letter 'n' within the text

No Comments

No Known Activations