INDEX

Explanations

references to "master" or "mastery" in various contexts

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

"master" or "Master"

np_acts-logits-general · gemini-2.0-flash

master and its compounds

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RefNanny

-0.61

RELATED

-0.57

idends

-0.55

epam

-0.53

,'\

-0.52

 priced

-0.52

挟

-0.51

ỡng

-0.51

Expenses

-0.50

bootstrapcdn

-0.50

POSITIVE LOGITS

mind

0.88

minds

0.87

stroke

0.79

 Masters

0.73

 MASTER

0.71

 maîtres

0.70

MIND

0.69

 masters

0.66

theless

0.66

piece

0.65

Activations Density 0.057%

references to "master" or "mastery" in various contexts

"master" or "Master"

master and its compounds

No Comments

No Known Activations