INDEX

Explanations

references to energy and its various implications or manifestations in different contexts

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

energy

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 NSCoder

-0.52

Vezi

-0.38

 nakalista

-0.38

 valable

-0.37

 dokon

-0.35

richTextPanel

-0.35

AndEndTag

-0.35

гән

-0.34

 actionPerformed

-0.33

 without

-0.33

POSITIVE LOGITS

 energy

1.16

Energy

1.13

energy

1.10

ENERGY

1.10

 ENERGY

1.09

 energia

1.05

 Energy

1.05

 energía

1.02

 Energie

0.98

 energi

0.98

Activations Density 0.012%

references to energy and its various implications or manifestations in different contexts

energy

No Comments

No Known Activations