INDEX

Explanations

expressions of personal gratitude and emotional reflection

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

Followed by first-person pronouns

np_acts-logits-general · gemini-2.0-flash

expressing appreciation or positive feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Билгалдахарш

-0.58

verwijspagina

-0.53

IGraphics

-0.52

__*/

-0.52

NameInMap

-0.52

пиона

-0.51

sieke

-0.51

 jspb

-0.50

jspb

-0.49

ibat

-0.49

POSITIVE LOGITS

 treasure

0.72

 treasures

0.64

Hentet

0.64

 honor

0.62

 honour

0.61

 cherish

0.59

 NSCoder

0.58

treasure

0.55

 mengucap

0.54

 treasured

0.53

Activations Density 0.146%

expressions of personal gratitude and emotional reflection

Followed by first-person pronouns

expressing appreciation or positive feelings

No Comments

No Known Activations