INDEX

Explanations

programming-related syntax, particularly in object-oriented languages

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

Code-related terms and symbols

np_acts-logits-general · gemini-2.0-flash

code 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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 kasarigan

-0.79

 pinulongan

-0.71

DockStyle

-0.69

最快更新

-0.66

WriteBarrier

-0.65

 getItemId

-0.64

хьтан

-0.63

 tartalomajánló

-0.63

 saites

-0.61

EndInit

-0.60

POSITIVE LOGITS

 orel

0.34

いただきたい

0.32

IContainer

0.32

 المعيارى

0.31

 trebui

0.31

 Dép

0.30

íč

0.29

transQ

0.29

様子

0.29

Activations Density 0.142%

programming-related syntax, particularly in object-oriented languages

Code-related terms and symbols

code structure

No Comments

No Known Activations