INDEX

Explanations

elements related to programming structures, particularly those involving nodes and event handling

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

code syntax and math variables

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

OGND

-0.52

transQ

-0.47

NOPQRST

-0.42

styleable

-0.42

 BorderLayout

-0.41

 esternos

-0.41

aarrggbb

-0.40

 strlen

-0.39

 betweenstory

-0.39

 erit

-0.38

POSITIVE LOGITS

ChildScrollView

0.65

 Roskov

0.57

ValueStyle

0.54

:✨

0.52

 HasFactory

0.47

BufferException

0.43

nofollow

0.42

})();

0.42

 *)__

0.41

Hauptartikel

0.41

Activations Density 0.015%

elements related to programming structures, particularly those involving nodes and event handling

code syntax and math variables

No Comments

No Known Activations