INDEX

Explanations

data related to online promotions and codes

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

"Code", often followed by related terms

np_acts-logits-general · gemini-2.0-flash

coupon codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 newOwner

-0.60

TemporalType

-0.57

saraba

-0.54

 doInBackground

-0.51

mography

-0.50

BagLayout

-0.50

iconque

-0.50

 Dalio

-0.50

subpackage

-0.48

PyExc

-0.48

POSITIVE LOGITS

 code

1.59

 codes

1.41

code

1.41

 Code

1.31

 Codes

1.25

codes

1.23

 CODE

1.22

Code

1.20

CODE

1.17

Codes

1.12

Activations Density 0.183%

data related to online promotions and codes

"Code", often followed by related terms

coupon codes

No Comments

No Known Activations