INDEX

Explanations

references to relationships with loved ones and themes of loss and mourning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.77

MigrationBuilder

-0.64

LookAnd

-0.63

haikusbot

-0.61

 mergeFrom

-0.61

ItemBackground

-0.58

 mouseY

-0.57

 ivelany

-0.56

webElement

-0.54

OrNil

-0.54

POSITIVE LOGITS

 loved

1.94

loved

1.52

 close

1.50

 Loved

1.47

 LOVED

1.40

 relatives

1.33

Loved

1.28

 dear

1.24

close

1.24

 Close

1.21

Activations Density 0.151%

references to relationships with loved ones and themes of loss and mourning

No Comments

No Known Activations