INDEX

Explanations

references to items or elements in a structured format, likely for data organization or programming contexts

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

"Item" or "Items"

np_acts-logits-general · gemini-2.0-flash

item

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

 GenerationType

-0.74

AndPassword

-0.71

}}}$

-0.69

 otomatig

-0.66

/\/

-0.64

ViewImports

-0.63

GraphicsUnit

-0.62

BagLayout

-0.61

 שוליים

-0.61

itinéraire

-0.61

POSITIVE LOGITS

 Items

1.00

items

0.99

 ITEMS

0.97

 items

0.95

 ITEM

0.84

 getItem

0.80

 Item

0.78

 itens

0.74

 newItem

0.72

Items

0.72

Activations Density 0.105%

references to items or elements in a structured format, likely for data organization or programming contexts

"Item" or "Items"

item

No Comments

No Known Activations