INDEX

Explanations

mentions of the word "passenger" in various contexts

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

passengers and travel

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 nyata

-0.41

 évidence

-0.41

 fonti

-0.40

 preservar

-0.37

 ámbitos

-0.36

 aikaa

-0.35

 trabalhar

-0.35

 Estadual

-0.35

 probado

-0.35

 acuerdos

-0.35

POSITIVE LOGITS

 passengers

2.02

 Passengers

1.93

Passengers

1.82

passengers

1.80

 Passenger

1.41

Passenger

1.38

 passenger

1.30

passenger

1.30

 passagers

1.28

 pasajeros

1.19

Activations Density 0.003%

mentions of the word "passenger" in various contexts

passengers and travel

No Comments

No Known Activations