INDEX

Explanations

terms associated with historical data records and backups

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

version history and bypasses

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

Pou

-0.32

घ

-0.29

 Seed

-0.28

Pou

-0.28

ตรี

-0.27

 Seeds

-0.27

punkten

-0.27

 tiết

-0.26

 Adverti

-0.26

np

-0.26

POSITIVE LOGITS

twimg

0.79

verwijspagina

0.61

 Roskov

0.60

rungsseite

0.57

 SwitchCompat

0.56

addCriterion

0.56

 يتيمه

0.56

tanleria

0.56

 replacement

0.52

 autorytatywna

0.52

Activations Density 0.088%

terms associated with historical data records and backups

version history and bypasses

No Comments

No Known Activations