INDEX

Explanations

instances where something is officially recognized or endorsed as meeting certain standards through a certification process

oai_token-act-pair · gpt-3.5-turbo

terms related to certification and certification processes

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

 scen

-0.70

Beh

-0.69

lihood

-0.68

hunt

-0.67

htar

-0.66

Ó

-0.66

axies

-0.64

 Torn

-0.63

bill

-0.63

beh

-0.62

POSITIVE LOGITS

 certification

1.22

 Certification

1.07

ificate

1.04

 cert

0.99

 certified

0.94

AFTA

0.88

ific

0.87

cert

0.86

 certify

0.85

ifications

0.85

Activations Density 0.024%

instances where something is officially recognized or endorsed as meeting certain standards through a certification process

terms related to certification and certification processes

No Comments

No Known Activations