INDEX

Explanations

phrases or elements related to categories and classifications in the context of film and media

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

"This Perfect", "Charts"

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

ServletException

-0.47

ngdoc

-0.42

GOTREF

-0.39

ROIT

-0.38

qvarna

-0.37

 étoient

-0.37

 NSCoder

-0.37

createCanvas

-0.36

 baseURL

-0.36

HostException

-0.35

POSITIVE LOGITS

 propOrder

0.55

expandindo

0.51

writeFieldEnd

0.50

 titles

0.47

 quedado

0.47

titleMargin

0.47

 atenta

0.45

pecabe

0.44

 Autorisations

0.44

ⓧ

0.44

Activations Density 0.179%

phrases or elements related to categories and classifications in the context of film and media

"This Perfect", "Charts"

No Comments

No Known Activations