INDEX

Explanations

variable assignments and comparisons in code

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

Variables (v, x, g, t) in code or math

np_acts-logits-general · gemini-2.0-flash

variable declaration or assignment

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

 wikipagina

-0.70

 autorytatywna

-0.68

 Taktlose

-0.66

 мәкал

-0.66

 Roskov

-0.65

MigrationBuilder

-0.64

 Wikiseite

-0.63

 kasarigan

-0.63

PreferredItem

-0.61



-0.60

POSITIVE LOGITS

 eventdata

0.38

 Dora

0.37

Насе

0.36

AntiForgeryToken

0.35

IRS

0.33

Lie

0.33

hObject

0.33

Slf

0.32

Lie

0.32

is

0.32

Activations Density 0.250%

variable assignments and comparisons in code

Variables (v, x, g, t) in code or math

variable declaration or assignment

No Comments

No Known Activations