INDEX

Explanations

code components and their relationships within a programming context

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

Text or code snippets with special characters

np_acts-logits-general · gemini-2.0-flash

latex math and code

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

Personensuche

-0.74

agisse

-0.68

 ویکی‌پدی

-0.66

 VIAF

-0.63

ConstraintMaker

-0.62

 كومونز

-0.60

 autorytatywna

-0.60

 indígen

-0.59

 ainfi

-0.58

abestanden

-0.56

POSITIVE LOGITS

Xna

0.33

twimg

0.31

StatusOK

0.27

gdx

0.27

getReal

0.26

 Helen

0.25

 पार

0.25

um

0.25

)"

0.25

TargetException

0.25

Activations Density 1.242%

code components and their relationships within a programming context

Text or code snippets with special characters

latex math and code

No Comments

No Known Activations