INDEX

Explanations

references to significant events or actions related to wildfire incidents and emergency responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

criptive

-0.53

colla

-0.49

sider

-0.47

hake

-0.47

 링크

-0.47

TestingModule

-0.45

 Figure

-0.44

 Vella

-0.43

multer

-0.43

onatos

-0.43

POSITIVE LOGITS

AP

0.70

})`

0.65

dpa

0.65

 propOrder

0.65

AP

0.64

enterOuterAlt

0.63

 poffible

0.62

dibles

0.61

 geox

0.60

 *)__

0.60

Activations Density 0.098%

references to significant events or actions related to wildfire incidents and emergency responses

No Comments

No Known Activations