INDEX

Explanations

references to films and filmmaking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 trône

-0.76

 étrang

-0.73

Vrij

-0.70

 Toler

-0.69

 Rache

-0.69

ANTAGE

-0.69

}".

-0.68

 Vrij

-0.68

ırlı

-0.66

]").

-0.65

POSITIVE LOGITS

 films

1.51

 film

1.47

 FILM

1.40

 Film

1.36

film

1.26

 Films

1.25

Film

1.18

 FILMS

1.18

FILM

1.16

Films

1.16

Activations Density 0.037%

references to films and filmmaking

No Comments

No Known Activations