INDEX

Explanations

attributes related to visibility settings in code

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

hidden or invisible

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

rrggbb

-0.51

 препратки

-0.44

Portály

-0.44

ModelMap

-0.42

 prisonniers

-0.40

 BoxFit

-0.40

 StatelessWidget

-0.40

 SEDS

-0.40

estacks

-0.40

bootstrapcdn

-0.40

POSITIVE LOGITS

EndContext

0.51

 nahilalakip

0.45

istoitu

0.45

hidden

0.45

INVISIBLE

0.44

UnitTesting

0.42

 hidden

0.42

ELES

0.42

hid

0.41

StoryboardSegue

0.41

Activations Density 0.009%

attributes related to visibility settings in code

hidden or invisible

No Comments

No Known Activations