INDEX

Explanations

words related to technical concepts and industry jargon

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 's'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

interstitial

-0.66

Compare

-0.63

 compromising

-0.63

 satur

-0.63

SIGN

-0.62

 eliminating

-0.62

atomic

-0.61

protect

-0.60

 Marshal

-0.59

saving

-0.59

POSITIVE LOGITS

ullivan

1.11

wered

0.93

kaya

0.87

 successor

0.87

ugu

0.85

 footsteps

0.85

 grandson

0.83

 daughter

0.82

ippi

0.82

 niece

0.80

Activations Density 0.163%

words related to technical concepts and industry jargon

occurrences of the letter 's'

No Comments

No Known Activations