INDEX

Explanations

references to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ValueStyle

-0.88

 Theſe

-0.83

TagMode

-0.80

IBarButtonItem

-0.79

IntoConstraints

-0.79

bewerken

-0.77

withIdentifier

-0.77

 chi̍t

-0.75

HomeAsUpEnabled

-0.75

rungsseite

-0.74

POSITIVE LOGITS

 products

1.27

products

1.18

Products

1.11

 Products

1.09

 PRODUCTS

0.89

PRODUCTS

0.88

 producten

0.86

 Produkte

0.82

productos

0.79

 productos

0.75

Activations Density 0.142%

references to products

No Comments

No Known Activations