INDEX

Explanations

punctuation marks and formatting symbols in the text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.87

存于互联网档案馆

-0.81

(;;)

-0.78

rainy

-0.78

 المعيارى

-0.77

TagMode

-0.77

^(@)

-0.74

cheinend

-0.73

 Abonnez

-0.71

GHI

-0.71

POSITIVE LOGITS

1.06

 ujednoznacz

1.05

–

1.00

awtextra

0.96

 disambiguazione

0.93

----------------

0.89

–

0.85

€“

0.83

Capítulo

0.81

‑

0.77

Activations Density 0.301%

punctuation marks and formatting symbols in the text

No Comments

No Known Activations