INDEX

Explanations

documentation and comments within code

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

code comments and structure

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

Билгалдахарш

-0.54

richTextPanel

-0.42

ApplicationTests

-0.41

UseVisualStyle

-0.39

modelBuilder

-0.38

Rujuakan

-0.37

 preven

-0.35

unknownFields

-0.34

parsedMessage

-0.34

__;

-0.33

POSITIVE LOGITS

:✨

0.67

AndEndTag

0.59

########.

0.57

 صوتيه

0.54

 تضيفلها

0.52

 CreateTagHelper

0.51

ⓧ

0.50

AddHtmlAttribute

0.48

rungsseite

0.47

 հղումներ

0.47

Activations Density 0.005%

documentation and comments within code

code comments and structure

No Comments

No Known Activations