INDEX

Explanations

non-English characters appearing in English text

oai_token-act-pair · gpt-3.5-turbo

characters or symbols that represent specific linguistic or cultural elements, particularly in non-Latin scripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 manif

-0.89

 disadvant

-0.83

 misunder

-0.80

 horizont

-0.80

 federation

-0.77

 stake

-0.76

 constitu

-0.75

 womb

-0.74

 proble

-0.74

 agre

-0.74

POSITIVE LOGITS

à¨

1.00

 ILCS

0.99

ı

0.93

ħ

0.92

®

0.91

ãĥ¥

0.90

à¥

0.89

æľ

0.88

¤

0.88

STAR

0.88

Activations Density 0.022%

non-English characters appearing in English text

characters or symbols that represent specific linguistic or cultural elements, particularly in non-Latin scripts

No Comments

No Known Activations