INDEX

Explanations

occurrences of rendering methods and their structure in code

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

Code-related keywords and function names

np_acts-logits-general · gemini-2.0-flash

render method calls

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Normdatei

-0.82

 queſta

-0.78

 ſche

-0.71

 ſta

-0.70

 Monfieur

-0.69

 itſelf

-0.68

 ſch

-0.68

OGND

-0.68

 referrerpolicy

-0.67

$_(

-0.67

POSITIVE LOGITS

setVerticalGroup

0.58

 initComponents

0.52

BuildContext

0.41

ScopeManager

0.40

wurf

0.32

 viewDidLoad

0.32

enterOuterAlt

0.31

IContainer

0.31

 getItemCount

0.31

runApp

0.30

Activations Density 0.016%

occurrences of rendering methods and their structure in code

Code-related keywords and function names

render method calls

No Comments

No Known Activations