INDEX

Explanations

concepts related to power dynamics and influence, particularly in leadership contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

зулта

-0.47

GEBURTS

-0.46

Joi

-0.46

 nahilalakip

-0.45

ArrowToggle

-0.44

 ausdrücklich

-0.43

gelopen

-0.42

莞

-0.39

宜

-0.38

 الاص

-0.38

POSITIVE LOGITS

 power

2.28

power

1.99

 POWER

1.77

Power

1.74

 Power

1.71

 powers

1.71

POWER

1.71

 potere

1.63

powers

1.56

 poder

1.53

Activations Density 0.445%

concepts related to power dynamics and influence, particularly in leadership contexts

No Comments

No Known Activations