INDEX

Explanations

elements related to movies and their attributes in a structured format

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

Code, API, and data strings

np_acts-logits-general · gemini-2.0-flash

popular movies, shows, and artists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

RectangleBorder

-0.73

kháu

-0.70

MemoryWarning

-0.65

awtextra

-0.62

Tē

-0.61

 ModelExpression

-0.60

 kaarangay

-0.59

nessed

-0.58

UnsafeEnabled

-0.58

Добрый

-0.57

POSITIVE LOGITS

 popularity

0.88

 popular

0.84

 Popular

0.75

 ratings

0.74

popular

0.74

 POPULAR

0.69

 rating

0.69

 recommendation

0.68

Popular

0.68

 favorites

0.68

Activations Density 0.254%

elements related to movies and their attributes in a structured format

Code, API, and data strings

popular movies, shows, and artists

No Comments

No Known Activations

elements related to movies and their attributes in a structured format

Code, API, and data strings

popular movies, shows, and artists

No Comments

No Known Activations