INDEX

Explanations

expressions of affection or love

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

"love"

np_acts-logits-general · gemini-2.0-flash

expressing positive sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Cigar

-0.51

 portico

-0.50

 Quay

-0.49

 Usher

-0.49

CGContext

-0.49

 Chanti

-0.47

 Somerset

-0.47

PCI

-0.47

BCA

-0.46

tiac

-0.46

POSITIVE LOGITS

 love

1.71

 LOVE

1.59

Love

1.54

love

1.50

 Love

1.47

LOVE

1.45

 loved

1.30

 loves

1.29

 Loves

1.24

loves

1.24

Activations Density 0.055%

expressions of affection or love

"love"

expressing positive sentiment

No Comments

No Known Activations