INDEX

Explanations

phrases related to superstitions and beliefs in luck

oai_token-act-pair · gpt-3.5-turbo

terms related to superstition

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

EStream

-0.84

-0.83

assetsadobe

-0.80

IRO

-0.75

hyde

-0.73

DragonMagazine

-0.73

 Sending

-0.68

 Commando

-0.67

ãĥ¼ãĥ³

-0.67

ktop

-0.65

POSITIVE LOGITS

itious

1.32

ructure

1.07

 superst

1.04

ition

0.99

arily

0.98

archy

0.94

ific

0.91

itionally

0.89

itions

0.88

ry

0.85

Activations Density 0.013%

phrases related to superstitions and beliefs in luck

terms related to superstition

No Comments

No Known Activations