INDEX

Explanations

Latex or code snippets containing symbols, numbers, and equal signs

oai_token-act-pair · gemini-2.0-flash

Mathematical symbols

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-1.02

IUrlHelper

-1.01

GEBURTSDATUM

-1.00

Personendaten

-0.98

tagHelperRunner

-0.95

AccessorTable

-0.90

 فريبيس

-0.85

 дописавши

-0.85

 صوتيه

-0.84

+#+#

-0.84

POSITIVE LOGITS

don

0.46

 indisponible

0.43

ka

0.43

'">

0.42

 didn

0.41

Mvc

0.40

“……”

0.40

allclose

0.38

ialis

0.38

isFunction

0.38

Activations Density 1.657%

Latex or code snippets containing symbols, numbers, and equal signs

Mathematical symbols

No Comments

No Known Activations