INDEX

Explanations

terms related to packaging and packaged items

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

"pack" or "package"

np_acts-logits-general · gemini-2.0-flash

pack

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

InjectAttribute

-0.75

 MotionEvent

-0.72

STI

-0.69

MigrationBuilder

-0.68

 <=",

-0.67

/\.

-0.67

Zur

-0.67

Uru

-0.66

DHT

-0.66

 Irrigation

-0.65

POSITIVE LOGITS

 PACK

1.34

 pack

1.28

 packs

1.27

 Pack

1.25

Pack

1.19

PACK

1.19

 packages

1.17

 package

1.16

pack

1.13

 Package

1.06

Activations Density 0.123%

terms related to packaging and packaged items

"pack" or "package"

pack

No Comments

No Known Activations