INDEX

Explanations

keywords related to certifications or certified processes

oai_token-act-pair · gpt-3.5-turbo

references to certification and its related terminology

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

lihood

-0.78

axies

-0.71

htar

-0.69

Ó

-0.69

ĸļ

-0.66

bill

-0.66

hunt

-0.65

 ãĤµ

-0.63

 scen

-0.63

fare

-0.62

POSITIVE LOGITS

 certification

1.18

 Certification

1.06

ificate

1.05

 cert

0.96

 certified

0.89

ific

0.88

ifications

0.87

iaries

0.82

AFTA

0.80

IFIED

0.79

Activations Density 0.030%

keywords related to certifications or certified processes

references to certification and its related terminology

No Comments

No Known Activations