INDEX

Explanations

references to energy and thermodynamic principles

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

energy in (kJ mol^-1)

np_acts-logits-general · gemini-2.0-flash

energy, work, heat

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

setAdapter

-0.61

 bäst

-0.58

 дож

-0.57

 JpaRepository

-0.57

 Mixtures

-0.55

στα

-0.52

 painted

-0.50

 paint

-0.50

 miroir

-0.50

icolor

-0.49

POSITIVE LOGITS

 energy

2.86

energy

2.52

 Energy

2.45

Energy

2.40

 ENERGY

2.19

ENERGY

1.96

 energies

1.91

énergie

1.88

 Energie

1.83

 energie

1.80

Activations Density 0.480%

references to energy and thermodynamic principles

energy in (kJ mol^-1)

energy, work, heat

No Comments

No Known Activations