INDEX

Explanations

words related to making a decision not to do something

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Springs

-0.69

CSS

-0.65

 Fountain

-0.62

ixel

-0.62

 Basics

-0.60

Kry

-0.60

 Journalism

-0.59

greSQL

-0.59

 Owner

-0.59

 Appears

-0.58

POSITIVE LOGITS

icably

1.23

epad

1.15

ifying

0.94

 necessarily

0.94

icable

0.92

hin

0.89

ifications

0.85

ices

0.85

ifies

0.85

withstanding

0.81

Activations Density 0.099%

words related to making a decision not to do something

No Comments

No Known Activations