INDEX

Explanations

terms related to programming structures and libraries, particularly for configuration and data handling

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

technical code and file paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

цездатний

-0.56

 typelib

-0.44

 ModelExpression

-0.43

ьаж

-0.42

 Paglinawan

-0.41

SafeMath

-0.41

/**

-0.41

tgz

-0.40

 فريبيس

-0.36

peq

-0.36

POSITIVE LOGITS

ReusableCell

0.55

ViewFeatures

0.54

TagMode

0.53

ADRID

0.49

ollectionView

0.46

 productivo

0.45

PreferredItem

0.44

ArrowToggle

0.44

 Waray

0.43

adă

0.42

Activations Density 0.147%

terms related to programming structures and libraries, particularly for configuration and data handling

technical code and file paths

No Comments

No Known Activations