INDEX

Explanations

mentions of holograms

oai_token-act-pair · gpt-3.5-turbo

terms related to holography

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

opath

-0.79

asted

-0.77

ologically

-0.75

wcsstore

-0.75

ivating

-0.73

ribute

-0.73

ursed

-0.71

amel

-0.71

onde

-0.70

cliffe

-0.69

POSITIVE LOGITS

EStream

1.00

 guiActiveUn

0.83

yip

0.76

 Aware

0.75

ãĥ¼ãĥĨãĤ£

0.74

 Pengu

0.73

0.71

yg

0.70

 Sinn

0.68

 Janeiro

0.67

Activations Density 0.041%

mentions of holograms

terms related to holography

No Comments

No Known Activations