INDEX

Explanations

phrases related to self-expression and personal experiences

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

Reflexive pronouns and possessive adjectives

np_acts-logits-general · gemini-2.0-flash

reflexive pronouns and own

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-0.77

complexType

-0.67

IUrlHelper

-0.65

 متعلقه

-0.61

StructEnd

-0.61

ftagPool

-0.60

setupUi

-0.55

TagMode

-0.55

 kasarigan

-0.54

 незавершена

-0.54

POSITIVE LOGITS

 himself

1.52

 herself

1.39

 myself

1.38

own

1.38

 yourself

1.29

 itself

1.28

himself

1.27

 ourselves

1.27

 themselves

1.23

自分も

1.22

Activations Density 0.352%

phrases related to self-expression and personal experiences

Reflexive pronouns and possessive adjectives

reflexive pronouns and own

No Comments

No Known Activations