INDEX

Explanations

references to personal ownership or possession

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

"own" appearing in text

np_acts-logits-general · gemini-2.0-flash

possessive "own"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tracce

-0.49

DbType

-0.47

sweise

-0.45

BrowserModule

-0.45

 réfrig

-0.43

了嗎

-0.42

racht

-0.42

ofür

-0.42

CURLOPT

-0.42

úsica

-0.41

POSITIVE LOGITS

own

1.32

Own

1.11

Own

1.07

own

1.04

OWN

0.98

 eigene

0.91

 egne

0.88

 eigenen

0.84

 egna

0.83

 włas

0.81

Activations Density 0.051%

references to personal ownership or possession

"own" appearing in text

possessive "own"

No Comments

No Known Activations