INDEX

Explanations

unusual or extreme descriptive words or phrases

oai_token-act-pair · gpt-3.5-turbo

quoted phrases or expressions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bending

-0.87

ĸļ

-0.83

 pacing

-0.77

 favor

-0.76

 periodic

-0.75

 Farn

-0.72

 raft

-0.71

 breaking

-0.69

 wrapping

-0.69

oun

-0.68

POSITIVE LOGITS

soDeliveryDate

1.49

BuyableInstoreAndOnline

1.30

true

1.17

inventoryQuantity

1.15

ItemThumbnailImage

1.14

false

1.10

WHERE

1.07

":"/

1.07

isSpecialOrderable

1.07

Putin

1.06

Activations Density 0.100%

unusual or extreme descriptive words or phrases

quoted phrases or expressions

No Comments

No Known Activations