INDEX

Explanations

technical definitions and structure declarations in a programming context

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

C definitions: #define S_... and #define V_.

np_acts-logits-general · gemini-2.0-flash

preprocessor defines and keywords

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 feroit

-0.59

 avoient

-0.55

 desmotivaciones

-0.55

 Administrativna

-0.54

 auroit

-0.53

<unused23>

-0.50

gypti

-0.50

<unused41>

-0.50

<unused28>

-0.50

<unused3>

-0.50

POSITIVE LOGITS

URLException

0.45

 EconPapers

0.41

XmlAccessType

0.35

당

0.33

LabelTagHelper

0.32

@"/

0.32

 sait

0.32

 surface

0.31

تقاوى

0.30

 vers

0.30

Activations Density 3.184%

technical definitions and structure declarations in a programming context

C definitions: #define S_... and #define V_.

preprocessor defines and keywords

No Comments

No Known Activations