INDEX

Explanations

references to products and services, particularly in eCommerce contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 DEVICE

-0.54

każ

-0.52

 Device

-0.51

)_/¯

-0.48

Tool

-0.47

gnant

-0.46

UserScript

-0.46

FormState

-0.45

huy

-0.44

 bong

-0.43

POSITIVE LOGITS

 products

2.56

products

1.93

 Products

1.86

 goods

1.70

Products

1.70

 produits

1.65

 producten

1.65

 PRODUCTS

1.63

 productos

1.62

 services

1.59

Activations Density 0.356%

references to products and services, particularly in eCommerce contexts

No Comments

No Known Activations