INDEX

Explanations

programming constructs or operations related to resource management

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

multi-lingual technical terms

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RefNanny

-0.57

IndentedString

-0.55

Autoritní

-0.54

OGND

-0.54

ModelSerializer

-0.52

ViewInit

-0.50

ResumeLayout

-0.50

InjectAttribute

-0.50

parsedMessage

-0.47

 Signalez

-0.46

POSITIVE LOGITS

 taas

0.44

ConstraintMaker

0.40

同上

0.39

Fordítás

0.39

issory

0.38

entral

0.37

 szint

0.37

 yine

0.37

Referencer

0.36

 disini

0.35

Activations Density 0.014%

programming constructs or operations related to resource management

multi-lingual technical terms

No Comments

No Known Activations