INDEX

Explanations

references to the Marvel Cinematic Universe (MCU) and its characters

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

fictional universes and franchises

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

 tele

-0.41

 Tele

-0.39

Tel

-0.35

 теле

-0.35

雷

-0.35

 Telephone

-0.34

Halt

-0.34

 Queen

-0.33

Dr

-0.33

Che

-0.33

POSITIVE LOGITS

 multiverse

0.66

 universes

0.66

rungsseite

0.61

universe

0.61

pédie

0.60

 AttributeSet

0.60

 universe

0.59

 universo

0.57

 Universe

0.57

 AssemblyCulture

0.56

Activations Density 0.020%

references to the Marvel Cinematic Universe (MCU) and its characters

fictional universes and franchises

No Comments

No Known Activations