INDEX

Explanations

technical terms and methods related to media playback and programming functions

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

Code, comments, or lists

np_acts-logits-general · gemini-2.0-flash

media playback actions

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 consag

-0.46

intios

-0.46

شاف

-0.45

 impresa

-0.43

CreateTable

-0.42

 linguagem

-0.41

exitRule

-0.41

 LoggerFactory

-0.41

dellín

-0.41

ectoria

-0.41

POSITIVE LOGITS

 play

1.54

 playback

1.49

 playing

1.47

 player

1.46

 Plays

1.42

 played

1.42

 plays

1.41

 Playing

1.39

 PLAY

1.37

play

1.35

Activations Density 0.260%

technical terms and methods related to media playback and programming functions

Code, comments, or lists

media playback actions

No Comments

No Known Activations