INDEX

Explanations

data structures and values related to dimensions and frames in programming contexts

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

<start_of_turn> user

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

GOT

-0.37

got

-0.37

HomeController

-0.35

fly

-0.34

Bac

-0.32

ⓧ

-0.31

Save

-0.31

options

-0.31

root

-0.31

User

-0.30

POSITIVE LOGITS

 CGRectMake

0.89

 CGRect

0.83

 الحره

0.72

contentLoaded

0.71

CGRectMake

0.71

 endforeach

0.62

 AssemblyTitle

0.61

principalColumn

0.61

 ComVisible

0.61

 CGPoint

0.60

Activations Density 0.003%

data structures and values related to dimensions and frames in programming contexts

<start_of_turn> user

No Comments

No Known Activations