INDEX

Explanations

proper nouns, specifically names of individuals and places

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

Preceding biographical information

np_acts-logits-general · gemini-2.0-flash

obituary or death dates

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

unhofer

-0.75

 Audiodateien

-0.71

 estekak

-0.68

CppCodeGen

-0.67

OGND

-0.62

hasMoreElements

-0.61

anmoins

-0.61

Personendaten

-0.61

 оригіналу

-0.60

sellors

-0.60

POSITIVE LOGITS

 passed

0.62

 Passed

0.59

 Obituary

0.56

Passed

0.54

 obituary

0.52

 zmar

0.52

setVerticalGroup

0.51

 died

0.50

 falleció

0.50

 meninggal

0.49

Activations Density 0.081%

proper nouns, specifically names of individuals and places

Preceding biographical information

obituary or death dates

No Comments

No Known Activations