INDEX

Explanations

specific terms and phrases related to programming syntax and structures

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

Mathematical or scientific notation

np_acts-logits-general · gemini-2.0-flash

tests after treatment

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

 Италијани

-0.71

 <<<<<<<<<<<<<<

-0.69

UserScript

-0.66

 Мексичка

-0.65

 endforeach

-0.60

aarrggbb

-0.59

دانشنامهٔ

-0.59

 esternos

-0.54

 tartalomajánló

-0.54

تقاوى

-0.53

POSITIVE LOGITS

 Physica

0.47

unuh

0.43

chiali

0.42

 materie

0.41

addCriterion

0.40

 conosco

0.40

 ochi

0.40

 ucap

0.40

 rekening

0.39

reathe

0.38

Activations Density 1.921%

specific terms and phrases related to programming syntax and structures

Mathematical or scientific notation

tests after treatment

No Comments

No Known Activations