INDEX

Explanations

elements related to data structures and manipulation

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

SQL queries with filtering conditions

np_acts-logits-general · gemini-2.0-flash

filtering with where

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utilisons

-0.42

存于互联网档案馆

-0.40

addTab

-0.39

KommentareTeilen

-0.38

 comuniques

-0.38

assertNull

-0.37

ouſ

-0.36

assertNotNull

-0.36

magaz

-0.36

PagerAdapter

-0.36

POSITIVE LOGITS

 filter

1.25

filter

1.17

 filtered

1.05

 Filter

1.02

 filtering

0.98

Filter

0.95

 filtro

0.95

 FILTER

0.93

 filters

0.92

 filtre

0.92

Activations Density 0.189%

elements related to data structures and manipulation

SQL queries with filtering conditions

filtering with where

No Comments

No Known Activations