INDEX

Explanations

sections of text that contain numerical data or formatting

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

stores and transactions

np_acts-logits-general · gemini-2.0-flash

store staff and customers

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

 Catawiki

-0.72

appartamento

-0.55

 privateKey

-0.52

realloc

-0.50

 exporters

-0.49

 fractured

-0.49

 fread

-0.48

 سب

-0.47

الدراسه

-0.46

 préc

-0.46

POSITIVE LOGITS

 staff

0.90

店内

0.79

店員

0.77

 customer

0.74

存于互联网档案馆

0.74

staff

0.73

 Staff

0.71

دانشنامهٔ

0.69

 cashier

0.69

来店

0.68

Activations Density 0.186%

sections of text that contain numerical data or formatting

stores and transactions

store staff and customers

No Comments

No Known Activations