INDEX

Explanations

numbers, especially those with decimal points or symbols like <

oai_token-act-pair · gemini-2.0-flash

words or phrases in foreign languages or transliterations

np_token-act-pair-logits · gpt-4o-mini

0

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 CreateTagHelper

-0.77

 للمعارف

-0.66

Packing

-0.54

 BoxFit

-0.54

LookAnd

-0.51

principalColumn

-0.50

 SqlDbType

-0.50

IBOutlet

-0.49

下载附件

-0.49

={<

-0.47

POSITIVE LOGITS

 imag

0.61

 Italijanski

0.61

 Shakspeare

0.57

LoadScene

0.56

bbene

0.55

 Senses

0.54

 Muscular

0.54

 neutrons

0.54

béco

0.54

 Muscles

0.54

Activations Density 1.976%

numbers, especially those with decimal points or symbols like <

words or phrases in foreign languages or transliterations

0

No Comments

No Known Activations