INDEX

Explanations

mentions of products and product-related components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

NUMX

-1.00

ſelves

-0.99

^(@)

-0.98

Efq

-0.98

 Anſ

-0.95

ReusableCell

-0.95

ſelf

-0.94

 Jefus

-0.94

 feroit

-0.94

 myſelf

-0.94

POSITIVE LOGITS

 products

1.18

 product

1.10

product

1.10

products

1.04

 Products

1.01

Products

1.00

Product

0.91

 produits

0.89

 Product

0.86

PRODUCTS

0.76

Activations Density 0.094%

mentions of products and product-related components

No Comments

No Known Activations