INDEX

Explanations

names or titles within text

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "name."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yrinth

-0.87

romy

-0.79

psey

-0.71

EMS

-0.70

gif

-0.70

isexual

-0.68

iaries

-0.68

elaide

-0.68

icult

-0.66

Js

-0.65

POSITIVE LOGITS

plates

1.27

plate

1.26

paces

1.01

 recognition

0.86

ames

0.85

akes

0.84

brand

0.83

tag

0.81

 aliases

0.79

lier

0.78

Activations Density 0.034%

names or titles within text

mentions of the word "name."

No Comments

No Known Activations