INDEX

Explanations

terms related to icons and symbols in various contexts

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

the word "icon" or "symbol"

np_acts-logits-general · gemini-2.0-flash

icon or symbol

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

addView

-0.67

atimes

-0.67

 Conducted

-0.67

ValueStyle

-0.64

 provato

-0.64

Péri

-0.63

Sortie

-0.62

PreInfinity

-0.62

Viited

-0.60

Hozzáférés

-0.60

POSITIVE LOGITS

 symbols

0.73

 symbole

0.70

 symbol

0.67

 icons

0.65

Symbols

0.65

 icon

0.64

symbols

0.63

 símbolo

0.63

 ICON

0.63

 emblema

0.62

Activations Density 0.127%

terms related to icons and symbols in various contexts

the word "icon" or "symbol"

icon or symbol

No Comments

No Known Activations