INDEX

Explanations

code comments and documentation within programming scripts

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

copyright headers and comments

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

ChildScrollView

-0.68

TagMode

-0.66

reactstrap

-0.60

Personensuche

-0.60

تقاوى

-0.58

 PeEnEo

-0.57

 Photocase

-0.57

 Vikipedi

-0.55

 estekak

-0.55

Chham

-0.55

POSITIVE LOGITS

 idéia

0.51

 aDecoder

0.40

 AssemblyTitle

0.35

 itemprop

0.34

 tirage

0.32

 chodzi

0.31

 talk

0.29

Cordialement

0.28

jadinya

0.28

 pory

0.28

Activations Density 0.006%

code comments and documentation within programming scripts

copyright headers and comments

No Comments

No Known Activations