INDEX

Explanations

common objects or items often associated with cases or containers

oai_token-act-pair · gpt-3.5-turbo

various types of cases and containers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

physical

-0.71

 alliances

-0.68

 Territories

-0.66

rians

-0.65

eatures

-0.65

 territories

-0.65

 valleys

-0.63

NetMessage

-0.63

 forests

-0.63

 Behavioral

-0.62

POSITIVE LOGITS

 holder

1.11

washer

0.94

case

0.89

 Holder

0.89

 maker

0.86

maid

0.85

 containing

0.84

cher

0.82

 heater

0.82

 shaped

0.82

Activations Density 0.318%

common objects or items often associated with cases or containers

various types of cases and containers

No Comments

No Known Activations