INDEX

Explanations

references to ownership and creation of personalized work or designs

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

Possessive pronouns followed by "own"

np_acts-logits-general · gemini-2.0-flash

possessive followed by own

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ssssssss

-0.41

getStringExtra

-0.41

lo

-0.41

utrients

-0.40

toFixed

-0.40

//

-0.40

ταν

-0.39

dalena

-0.39

 EventArgs

-0.38

edan

-0.37

POSITIVE LOGITS

own

2.91

Own

2.39

Own

2.32

 eigene

2.27

own

2.23

 eigenen

2.18

 sendiri

2.08

 propia

2.06

 włas

2.05

自己的

2.04

Activations Density 0.434%

references to ownership and creation of personalized work or designs

Possessive pronouns followed by "own"

possessive followed by own

No Comments

No Known Activations