INDEX

Explanations

names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "name" in various forms

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

yrinth

-0.89

psey

-0.75

EMS

-0.73

elaide

-0.73

irth

-0.71

isoft

-0.68

asio

-0.68

istar

-0.67

icult

-0.66

ĸļ

-0.66

POSITIVE LOGITS

plates

1.39

plate

1.22

paces

1.21

names

1.00

paced

0.97

brand

0.91

 names

0.84

ames

0.83

 aliases

0.83

calling

0.81

Activations Density 0.043%

names

occurrences of the word "name" in various forms

No Comments

No Known Activations