INDEX

Explanations

references to actions and functionality in programming, particularly related to user interface interactions

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

"panel" (GUI, plots, etc.)

np_acts-logits-general · gemini-2.0-flash

panel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ArrowToggle

-0.52

 متعلقه

-0.47

 Cruz

-0.46

friend

-0.46

hores

-0.46

 fragrance

-0.44

 doGet

-0.43

(;;

-0.42

 Hochschule

-0.41

 promis

-0.41

POSITIVE LOGITS

 panel

4.16

 Panel

3.80

panel

3.67

Panel

3.53

 PANEL

3.33

 panels

3.21

PANEL

2.98

 Panels

2.95

panels

2.56

Panels

2.50

Activations Density 0.130%

references to actions and functionality in programming, particularly related to user interface interactions

"panel" (GUI, plots, etc.)

panel

No Comments

No Known Activations