INDEX

Explanations

terms associated with fuel types and consumption

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

"fuel."

np_acts-logits-general · gemini-2.0-flash

fuel, injection, cell, efficiency, supply

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

ViewFeatures

-0.69

 reaſon

-0.61

 Elector

-0.60

rientes

-0.60

Aholisi

-0.56

enterOuterAlt

-0.56

Попис

-0.56

كويكب

-0.54

ineno

-0.53

ophon

-0.53

POSITIVE LOGITS

 supply

0.66

 consumption

0.57

 tank

0.57

]-->

0.55

 Supply

0.54

 Saving

0.52

 Pingback

0.51

efficient

0.50

DispatchToProps

0.50

LESS

0.49

Activations Density 0.111%

terms associated with fuel types and consumption

"fuel."

fuel, injection, cell, efficiency, supply

No Comments

No Known Activations