INDEX

Explanations

terms related to emergency risk communication and guidelines

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

 BorderSide

-0.48

TagMode

-0.47

ところ

-0.46

preventDefault

-0.44

AxisAlignment

-0.44

SourceChecksum

-0.43

didSet

-0.42

POSITIVE LOGITS

RefNanny

0.72

的其他

0.68

تقاوى

0.65

ThroughAttribute

0.65

anglès

0.65

 olmayan

0.63

ValueStyle

0.61

NameInMap

0.61

 itself

0.61

 تانيه

0.61

Activations Density 1.250%

terms related to emergency risk communication and guidelines

No Comments

No Known Activations