INDEX

Explanations

incidents related to accidents and fatalities

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

automobile accident deaths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 paño

-0.43

 invokingState

-0.42

 besky

-0.40

 kasarigan

-0.39

 kaarangay

-0.39

 península

-0.38

Dimensões

-0.38

 virtud

-0.38

rrggbb

-0.36

 bahía

-0.35

POSITIVE LOGITS

ListItemIcon

0.52

WebElementEntity

0.50

 Highway

0.45

 recie

0.45

AsUp

0.44

 deaths

0.44

SharedDtor

0.44

parsedMessage

0.43

 fatality

0.43

 fatal

0.42

Activations Density 0.002%

incidents related to accidents and fatalities

automobile accident deaths

No Comments

No Known Activations