INDEX

Explanations

references to characters and narratives that involve heroism and personal transformation

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

Follows "be", "became", or "as"

np_acts-logits-general · gemini-2.0-flash

hero royalty superstar celebrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

expandindo

-0.71

Билгалдахарш

-0.69

 TabLayout

-0.59

ByVersion

-0.56

PreferredItem

-0.55

aarrggbb

-0.55

 AssemblyProduct

-0.55

stdc

-0.55

findpost

-0.54

 propOrder

-0.54

POSITIVE LOGITS

 hero

0.96

 superstar

0.94

 superhero

0.85

 king

0.80

 super

0.79

 superstars

0.77

 heroes

0.73

 royalty

0.73

 celebrity

0.73

hero

0.73

Activations Density 0.281%

references to characters and narratives that involve heroism and personal transformation

Follows "be", "became", or "as"

hero royalty superstar celebrity

No Comments

No Known Activations