INDEX

Explanations

elements that highlight uniqueness and differentiation among subjects or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Económica

-0.48

 hyvä

-0.42

 исправ

-0.40

ite

-0.40

yasi

-0.39

 Estatal

-0.39

 nerfs

-0.39

hdys

-0.38

Lei

-0.38

尉

-0.38

POSITIVE LOGITS

 uniqueness

1.50

 unique

1.50

unique

1.34

 Unique

1.33

Unique

1.29

 uniquely

1.26

 UNIQUE

1.22

 distin

1.09

 distinctive

1.08

 uniques

1.06

Activations Density 0.318%

elements that highlight uniqueness and differentiation among subjects or products

No Comments

No Known Activations