INDEX

Explanations

phrases indicating a state of incompleteness or uncertainty

oai_token-act-pair · gpt-3.5-turbo

phrases indicating something that has not yet occurred or been completed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soDeliveryDate

-0.88

 Favor

-0.70

channelAvailability

-0.65

still

-0.64

DragonMagazine

-0.64

Veh

-0.64

 Skip

-0.63

¸

-0.62

 delaying

-0.61

wolves

-0.60

POSITIVE LOGITS

 formally

0.95

 officially

0.91

icable

0.89

 finalized

0.88

 fully

0.86

 satisf

0.83

 finished

0.78

 substant

0.78

 decide

0.78

material

0.77

Activations Density 0.079%

phrases indicating a state of incompleteness or uncertainty

phrases indicating something that has not yet occurred or been completed

No Comments

No Known Activations