INDEX

Explanations

terms related to power and energy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 doubtnut

-0.95

 betweenstory

-0.88

 Jams

-0.84

Personensuche

-0.83

 HasFactory

-0.81

thâu

-0.81

 Monks

-0.80

septic

-0.79

 дописавши

-0.79

Tembelea

-0.77

POSITIVE LOGITS

 power

3.20

 Power

3.10

Power

2.99

power

2.94

 POWER

2.74

POWER

2.72

powers

2.18

 powers

2.15

 Powers

2.14

Powers

2.02

Activations Density 0.069%

terms related to power and energy

No Comments

No Known Activations