INDEX

Explanations

specific terms and concepts related to mental health, concentration, and social interactions

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

Technical or scientific properties

np_acts-logits-general · gemini-2.0-flash

properties, printing, sew, driver

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.58

 nahilalakip

-0.56

 pinulongan

-0.56

 autorytatywna

-0.51

TypedDataSet

-0.51

idopsis

-0.50

InitVars

-0.48

 gela

-0.47

archiviato

-0.47

 esternos

-0.47

POSITIVE LOGITS

TagHelper

0.38

 brukes

0.33

BrowserModule

0.32

bebasan

0.32

 APPLIED

0.31

 Deum

0.31

 teus

0.30

 applied

0.30

 used

0.30

FormsModule

0.30

Activations Density 0.649%

specific terms and concepts related to mental health, concentration, and social interactions

Technical or scientific properties

properties, printing, sew, driver

No Comments

No Known Activations