INDEX

Explanations

information related to structured data and product attributes

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

Product specifications and attributes

np_acts-logits-general · gemini-2.0-flash

product name or id

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

ffilm

-0.53

 propOrder

-0.50

StoryboardSegue

-0.49

findpost

-0.49

Siapa

-0.48

ixo

-0.48

 Româ

-0.48

 InputDecoration

-0.47

RenderAtEndOf

-0.47

 AppDelegate

-0.46

POSITIVE LOGITS

 product

1.10

SKU

1.07

SKU

1.04

 inventory

0.98

 Product

0.96

sku

0.93

 stock

0.93

product

0.93

Product

0.91

 price

0.90

Activations Density 0.155%

information related to structured data and product attributes

Product specifications and attributes

product name or id

No Comments

No Known Activations