INDEX

Explanations

terms related to net values in financial or scientific contexts

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

"net" followed by a capital letter

np_acts-logits-general · gemini-2.0-flash

net N, worth, work, cost, MHC, wire

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chronique

-0.60

 Monfieur

-0.58

ñora

-0.56

 faſt

-0.56

 ―――――

-0.56

ثيق

-0.56

paravant

-0.56

 itſelf

-0.55

 Theſe

-0.54

 BorderRadius

-0.54

POSITIVE LOGITS

NET

0.84

Ne

0.83

posedge

0.81

Net

0.78

Ne

0.76

contentLoaded

0.71

ne

0.71

Net

0.70

NET

0.70

NE

0.68

Activations Density 0.150%

terms related to net values in financial or scientific contexts

"net" followed by a capital letter

net N, worth, work, cost, MHC, wire

No Comments

No Known Activations