INDEX

Explanations

references to products and product-related terms

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

"product"

np_acts-logits-general · gemini-2.0-flash

product and its context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.38

]=="

-0.38

 levanta

-0.37

Berikut

-0.37

 invierno

-0.36

 způ

-0.36

,\,\

-0.35

<table>

-0.35

 cérebro

-0.35

 zimní

-0.35

POSITIVE LOGITS

 product

1.13

 Product

1.09

 getProduct

1.09

Product

1.04

product

1.02

 Products

0.98

 ProductService

0.97

 PRODUCT

0.95

ProductService

0.95

 products

0.94

Activations Density 0.054%

references to products and product-related terms

"product"

product and its context

No Comments

No Known Activations