INDEX

Explanations

terms related to telecommunications and devices that use or promote telecommunication

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

"tele-" prefix

np_acts-logits-general · gemini-2.0-flash

telecommunication, teleportation, telepaths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

interopRequire

-0.57

 Pixabay

-0.54

Facades

-0.52

HtmlAttribute

-0.50

ledem

-0.50

 CreateTagHelper

-0.50

ServletRequest

-0.49

 solida

-0.47

cjs

-0.47

resave

-0.47

POSITIVE LOGITS

 Tele

1.03

 tele

0.97

Tele

0.90

 TELE

0.87

Teles

0.71

tele

0.71

 teleport

0.71

 Teles

0.71

 ویکی‌پدی

0.69

TELE

0.69

Activations Density 0.049%

terms related to telecommunications and devices that use or promote telecommunication

"tele-" prefix

telecommunication, teleportation, telepaths

No Comments

No Known Activations