INDEX

Explanations

phrases related to plugging in or connecting devices and components

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

"plug" or its variations

np_acts-logits-general · gemini-2.0-flash

plug and plug-in

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



-0.58

 surla

-0.56

OGND

-0.49

UserScript

-0.48

usercontent

-0.46

ModelAdmin

-0.42

ApiModel

-0.42

rslt

-0.42

 Haller

-0.41

yyj

-0.41

POSITIVE LOGITS

 plug

1.83

 Plug

1.70

Plug

1.67

plug

1.59

 plugs

1.57

 plugged

1.50

 plugging

1.49

plugs

1.41

 PLUG

1.39

PLUG

1.29

Activations Density 0.140%

phrases related to plugging in or connecting devices and components

"plug" or its variations

plug and plug-in

No Comments

No Known Activations