INDEX

Explanations

identifiers or labels related to employee management and gamification

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

following `<start_of_turn>user`

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

 surla

-0.58

 يتيمه

-0.50

ագրություններ

-0.49

awaiter

-0.47

internalType

-0.46

Atsauces

-0.45

featureID

-0.43

 FetchType

-0.43

 kaynağından

-0.43

 CGPoint

-0.43

POSITIVE LOGITS

 defaultstate

0.50

WillAppear

0.47

 nahilalakip

0.44

setVerticalGroup

0.42

GeoNames

0.41

 noDo

0.39

LookAnd

0.38

Abit

0.38

IndentedString

0.37

MemoryWarning

0.37

Activations Density 0.000%

identifiers or labels related to employee management and gamification

following `<start_of_turn>user`

No Comments

No Known Activations