INDEX

Explanations

proper nouns related to individuals or entities

oai_token-act-pair · gpt-3.5-turbo

phrases that highlight exclusivity or uniqueness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

actionDate

-0.88

assetsadobe

-0.77

gradient

-0.72

 DRAG

-0.69

 Reef

-0.69

 Skydragon

-0.68

rex

-0.68

rence

-0.64

uay

-0.64

complex

-0.64

POSITIVE LOGITS

 ever

1.00

ever

0.81

 EVER

0.78

 quir

0.77

ably

0.74

 sane

0.72

 reliably

0.70

 exempt

0.70

nor

0.69

 interven

0.68

Activations Density 0.168%

proper nouns related to individuals or entities

phrases that highlight exclusivity or uniqueness

No Comments

No Known Activations