INDEX

Explanations

references to movies and the film industry

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

movies and films

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

astricht

-0.43

 Upper

-0.40

 redes

-0.39

 upper

-0.38

Upper

-0.37

Quiet

-0.37

的下

-0.37

 ниж

-0.36

 Outer

-0.36

 верх

-0.36

POSITIVE LOGITS

 films

1.12

 movies

1.07

 cinema

1.06

 film

1.05

 filmmakers

1.02

Films

1.01

 filmmaking

1.01

 movie

1.00

 Film

0.98

film

0.98

Activations Density 0.048%

references to movies and the film industry

movies and films

No Comments

No Known Activations