INDEX

Explanations

elements related to programming structures and data management

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

Code-related tokens after specific words

np_acts-logits-general · gemini-2.0-flash

code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

PerformLayout

-1.04

 للمعارف

-0.91

amaño

-0.86

lapsingToolbar

-0.86

 ویکی‌پدیا

-0.86

таратура

-0.84

 AppModule

-0.82

DockStyle

-0.82

principalColumn

-0.81

 ILogger

-0.78

POSITIVE LOGITS

0.37

0.30

 whatnot

0.28

cetamol

0.27

0.26

ル

0.26

—

0.26

ع

0.25

{{\

0.25

 löytyy

0.25

Activations Density 0.379%

elements related to programming structures and data management

Code-related tokens after specific words

code constructs

No Comments

No Known Activations