INDEX

Explanations

references to code libraries and programming imports

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

code snippets and programming terms

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

Negative Logits

MessageTagHelper

-0.50

tagext

-0.47

 Fowler

-0.47

ngrx

-0.45

postsleuth

-0.44

endphp

-0.43

webElementXpaths

-0.43

ایناق

-0.42

nloa

-0.41

MLLoader

-0.41

POSITIVE LOGITS

UIKit

0.75

 UIKit

0.65

 initComponents

0.62

VersionUID

0.58

 للاسماء

0.56

 kasarigan

0.50

été

0.49

 vocales

0.48

 '\\;'

0.47

 fubject

0.47

Activations Density 0.001%

references to code libraries and programming imports

code snippets and programming terms

No Known Activations