INDEX

Explanations

terms related to "master" and hierarchy in power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Zwiebel

-0.68

idends

-0.67

emplos

-0.66

 alimentaire

-0.66

epam

-0.66

avion

-0.65

ณ์

-0.62

oult

-0.62

 anticoag

-0.61

 drog

-0.61

POSITIVE LOGITS

 Masters

1.52

 masters

1.49

 MASTER

1.44

 Master

1.35

MASTER

1.35

Masters

1.32

 master

1.27

Master

1.26

master

1.15

masters

1.15

Activations Density 0.068%

terms related to "master" and hierarchy in power dynamics

No Comments

No Known Activations