INDEX

Explanations

references to the plot and its development within narratives

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

plot and storylines

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

multer

-0.66

tonsoft

-0.58

HasAnnotation

-0.57

 unary

-0.57

delwed

-0.56

 Nickel

-0.56

MethodManager

-0.56

 Challenger

-0.55

الحياه

-0.54

ImageIO

-0.54

POSITIVE LOGITS

 storyline

0.68

 plot

0.67

 story

0.64

 plans

0.61

 storylines

0.60

 plan

0.57

plot

0.55

 scénario

0.54

Plot

0.54

 сю

0.53

Activations Density 0.011%

references to the plot and its development within narratives

plot and storylines

No Comments

No Known Activations