INDEX

Explanations

references to episodes and their details in a television series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

uertos

-0.44

silien

-0.42

unz

-0.42

impose

-0.42

 gama

-0.42

UNTS

-0.42

 CreateTagHelper

-0.41

йтесь

-0.40

nija

-0.39

 reda

-0.39

POSITIVE LOGITS

 episode

1.93

 episodes

1.64

episode

1.62

Episode

1.59

 Episode

1.58

 Episodes

1.41

 EPISODE

1.34

 épisode

1.29

episodes

1.26

Episodes

1.24

Activations Density 0.214%

references to episodes and their details in a television series

No Comments

No Known Activations