INDEX

Explanations

terms and phrases related to holograms

oai_token-act-pair · gpt-3.5-turbo

terms related to holography and its applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

weeney

-0.77

Fed

-0.73

Raf

-0.68

 Belt

-0.68

STD

-0.65

ctive

-0.64

âķĲâķĲ

-0.64

vier

-0.64

-0.63

AE

-0.63

POSITIVE LOGITS

 holog

1.50

raphic

1.00

Ħ¢

0.92

 headsets

0.80

iov

0.79

metry

0.75

etooth

0.75

 headset

0.73

 challeng

0.72

ram

0.71

Activations Density 0.008%

terms and phrases related to holograms

terms related to holography and its applications

No Comments

No Known Activations