INDEX

Explanations

words and phrases related to management, leadership, and Human Resources.

oai_token-act-pair · gemini-2.0-flash

technical terms or jargon

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

Human resources, management

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

 companies

-1.52

 company

-1.44

 Companies

-1.42

Companies

-1.41

 businesses

-1.41

 corporations

-1.38

companies

-1.34

 Unternehmen

-1.34

Businesses

-1.33

 Businesses

-1.32

POSITIVE LOGITS

 ProtoMessage

0.57

ⓧ

0.55

TestTools

0.55

offsetof

0.53

 مرئيه

0.52

 生命周期

0.50

msgs

0.48

partement

0.47

AsUp

0.46

ccoli

0.46

Activations Density 0.995%

words and phrases related to management, leadership, and Human Resources.

technical terms or jargon

Human resources, management

No Comments

No Known Activations