INDEX

Explanations

words related to locations or entities with "ara" in them

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Dara" and variations of Arabic names and terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rium

-0.65

ullivan

-0.64

lor

-0.63

TRY

-0.63

rer

-0.62

regor

-0.62

lers

-0.62

LER

-0.61

rers

-0.59

low

-0.59

POSITIVE LOGITS

uthor

1.13

Ã¯

0.97

ishi

0.89

esthetic

0.86

qual

0.86

esthesia

0.85

heed

0.85

illac

0.84

resh

0.83

ean

0.82

Activations Density 0.098%

words related to locations or entities with "ara" in them

instances of the term "Dara" and variations of Arabic names and terms

No Comments

No Known Activations