INDEX

Explanations

specific programming syntax and structures

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

UI/code snippets

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

Not in Any Lists

No Comments

Negative Logits

 parcial

-0.31

 communs

-0.29

 fidèles

-0.29

 régulier

-0.28

pleft

-0.28

 animación

-0.28

 Función

-0.28

 calentamiento

-0.28

 múltiple

-0.28

 calça

-0.27

POSITIVE LOGITS

GTCX

0.66

ChildScrollView

0.64

AnimationsModule

0.64

 autorytatywna

0.61

 informée

0.60

UserScript

0.59

msgTypes

0.57

 &___

0.54

Bump

0.54

WillAppear

0.54

Activations Density 0.017%

specific programming syntax and structures

UI/code snippets

No Comments

No Known Activations