INDEX

Explanations

expressions related to personal favorites or preferences

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

"favorite" or "favourite"

np_acts-logits-general · gemini-2.0-flash

favorite things

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ResumeLayout

-0.48

-0.47

 ziua

-0.47

graphique

-0.47

ende

-0.46

 judiciaire

-0.45

 behov

-0.44

ers

-0.44

},

-0.43

POSITIVE LOGITS

 <<<<<<<<<<<<<<

1.03

 favorites

1.02

 Favorites

1.00

favorites

0.92

 favorite

0.92

favorite

0.88

 Favorite

0.88

 FAVORITE

0.85

 pastime

0.85

Favorite

0.84

Activations Density 0.093%

expressions related to personal favorites or preferences

"favorite" or "favourite"

favorite things

No Comments

No Known Activations