INDEX

Explanations

phrases related to being a son of someone or something

oai_token-act-pair · gpt-3.5-turbo

references to familial relationships, particularly focusing on the phrase "son of" and its variations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nels

-0.81

aceous

-0.80

uden

-0.75

pport

-0.73

ickr

-0.73

ngth

-0.73

ukong

-0.68

wcs

-0.68

 defenses

-0.68

Downloadha

-0.67

POSITIVE LOGITS

 immigrants

0.79

 immigrant

0.71

 hers

0.71

 Emmy

0.70

 wealthy

0.69

 former

0.69

Cul

0.69

 millionaire

0.68

 deceased

0.68

 Hispanic

0.67

Activations Density 0.050%

phrases related to being a son of someone or something

references to familial relationships, particularly focusing on the phrase "son of" and its variations

No Known Activations