INDEX

Explanations

class definitions in code

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

C++ code and comments

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InjectAttribute

-0.59

 '\\;'

-0.52

 GenerationType

-0.51

PreInfinity

-0.48

ValueStyle

-0.46

BeginInit

-0.46

ßerdem

-0.41

WithIOException

-0.41

 mView

-0.40

DataAnnotations

-0.40

POSITIVE LOGITS

Спољашње

0.43

 Reverso

0.41

newtheorem

0.40

 leva

0.40

RefNanny

0.39

cmos

0.39

mazda

0.38

setCellValue

0.38

 ArrayAdapter

0.38

 Lemma

0.38

Activations Density 0.055%

class definitions in code

C++ code and comments

No Comments

No Known Activations