INDEX

Explanations

references to scenes and their descriptions in a narrative or script format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 VIAF

-0.75

multer

-0.60

 насељу

-0.56

Grind

-0.56

tadır

-0.55

 سكانية

-0.53

antMatchers

-0.53

wurde

-0.52

 noqa

-0.52

Datuak

-0.52

POSITIVE LOGITS

 scenes

1.66

 scene

1.59

 SCENE

1.49

 Scene

1.43

 Scenes

1.41

SCENE

1.35

scene

1.32

Scenes

1.25

SceneManagement

1.24

scenes

1.20

Activations Density 0.105%

references to scenes and their descriptions in a narrative or script format

No Comments

No Known Activations