INDEX

Explanations

names or titles related to law enforcement or legal roles

oai_token-act-pair · gpt-3.5-turbo

references to legal and governmental roles or titles

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

Not in Any Lists

No Comments

Negative Logits

 tumble

-0.89

 shave

-0.72

 womb

-0.72

 simulator

-0.71

 nipple

-0.71

zsche

-0.71

 curl

-0.70

 haircut

-0.70

wob

-0.70

tumblr

-0.69

POSITIVE LOGITS

 Deputy

1.27

 Assistant

1.25

 Minister

1.23

 Secretary

1.22

 Inspector

1.19

 Commissioner

1.19

 Investigator

1.19

 Officer

1.16

 Chief

1.15

 Attorney

1.15

Activations Density 0.187%

names or titles related to law enforcement or legal roles

references to legal and governmental roles or titles

No Comments

No Known Activations