INDEX

Explanations

references to figures or images within the text

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

figure references and links

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

 ISNI

-0.50

nestjs

-0.48

 <<<<<<<<<<<<<<

-0.44

UnusedPrivate

-0.43

 незавершена

-0.42

 gyhoeddwyd

-0.40

TagMode

-0.39

Claw

-0.39

Blank

-0.39

 CallOverrides

-0.39

POSITIVE LOGITS

 AssemblyVersion

0.52



0.50

WritableDatabase

0.48

 AssemblyCulture

0.46

verwijspagina

0.46

indari

0.46

Diweddarwch

0.44

GEBURTSDATUM

0.43

最快更新

0.41

PreferredItem

0.41

Activations Density 0.002%

references to figures or images within the text

figure references and links

No Comments

No Known Activations