INDEX

Explanations

mentions of health, wellness, and local community features

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

geographical proximity

np_acts-logits-general · gemini-2.0-flash

nearby, neighboring, adjacent

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

queryInterface

-0.65

#+#

-0.64

 InputDecoration

-0.63

SharedCtor

-0.60

########.

-0.60

}`}>

-0.58

 puissiez

-0.57

OPSIS

-0.57

abstractmethod

-0.57

findpost

-0.55

POSITIVE LOGITS

 nearby

1.74

 neighboring

1.27

 Nearby

1.26

nearby

1.26

 neighbouring

1.24

Nearby

1.22

 neighbors

1.10

 neighbor

1.09

 adjacent

1.09

 neighbour

1.05

Activations Density 0.243%

mentions of health, wellness, and local community features

geographical proximity

nearby, neighboring, adjacent

No Comments

No Known Activations