INDEX

Explanations

references to module configuration in code

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

Code, modules, or assembly-related tokens

np_acts-logits-general · gemini-2.0-flash

NgModule, BrowserModule, CommonModule

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

parsedMessage

-0.48

ulemon

-0.47

contentLoaded

-0.45

 dAtA

-0.45

readLine

-0.43

RTHOOK

-0.43

DMETHOD

-0.42

 يتيمه

-0.41

jsonwebtoken

-0.41

imanapun

-0.40

POSITIVE LOGITS

 NgModule

1.96

NgModule

1.84

 CommonModule

0.96

 BrowserModule

0.91

 TestBed

0.83

CommonModule

0.80

BrowserModule

0.78

RoutingModule

0.71

FormsModule

0.69

AnimationsModule

0.69

Activations Density 0.024%

references to module configuration in code

Code, modules, or assembly-related tokens

NgModule, BrowserModule, CommonModule

No Comments

No Known Activations