INDEX

Explanations

location descriptors related to parts of objects or features in a spatial context

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

Location or position

np_acts-logits-general · gemini-2.0-flash

sides, corners, and ends

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

 EconPapers

-0.79

-0.73

ormais

-0.72

 vuitton

-0.71

ſelves

-0.69

makeConstraints

-0.68

 ſta

-0.68

 cauſe

-0.68

transQ

-0.68

retudo

-0.68

POSITIVE LOGITS

of

0.55

IContainer

0.52

 corner

0.46

الحياه

0.42

نیم

0.40

homonymie

0.40

יצ

0.39

 inside

0.38

やや

0.38

Activations Density 0.204%

location descriptors related to parts of objects or features in a spatial context

Location or position

sides, corners, and ends

No Comments

No Known Activations