INDEX

Explanations

phrases and terms related to accounting and service packages

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

Code package declarations

np_acts-logits-general · gemini-2.0-flash

package

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

OGND

-0.44

évaluateur

-0.43

__':

-0.41

AccessorTable

-0.41

InjectAttribute

-0.39

yntaxException

-0.39

цезда

-0.39

__':

-0.39

 needle

-0.37

 Wiktionnaire

-0.36

POSITIVE LOGITS

 package

2.94

 packages

2.73

 Package

2.63

package

2.44

 Packages

2.41

 PACKAGE

2.41

Package

2.36

 paket

2.17

PACKAGE

2.14

packages

2.13

Activations Density 0.138%

phrases and terms related to accounting and service packages

Code package declarations

package

No Comments

No Known Activations