INDEX

Explanations

terms related to wildfires and their impact on structures and evacuations

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

Fire and blazes

np_acts-logits-general · gemini-2.0-flash

burning and blaze

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Agnew

-0.52

elemField

-0.52

raba

-0.52

 Diarrhea

-0.48

 élastique

-0.44

 hígado

-0.44

otonic

-0.44

amond

-0.44

 bacterio

-0.44

rota

-0.44

POSITIVE LOGITS

 fire

1.52

 flames

1.33

 fires

1.29

 arson

1.25

 Fire

1.22

Fire

1.21

fire

1.19

 flame

1.16

 smoke

1.15

 burning

1.14

Activations Density 0.210%

terms related to wildfires and their impact on structures and evacuations

Fire and blazes

burning and blaze

No Comments

No Known Activations