INDEX

Explanations

relationships and connections between different entities in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

IsContent

-0.98

 Савезне

-0.86

 propOrder

-0.83

PreferredItem

-0.81

 Мексичка

-0.78

 '\\;'

-0.77

oredCriteria

-0.76

ValueStyle

-0.76

MigrationBuilder

-0.75

الحياه

-0.71

POSITIVE LOGITS

 below

0.42

 oublié

0.40

Below

0.40

kari

0.39

here

0.39

 proprio

0.38

ẨM

0.38

irsk

0.38

 justement

0.38

 recently

0.37

Activations Density 1.435%

relationships and connections between different entities in discussions

No Comments

No Known Activations