INDEX

Explanations

relationships between characters and their roles within narratives

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

just, simply, or merely

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

 INTERPRET

-0.48

-0.41

 interpretación

-0.41

 vertrou

-0.40

 équilibr

-0.40

 MainAxisSize

-0.39

EDEFAULT

-0.39

 entiendo

-0.39

 Vertra

-0.39

 Spannung

-0.39

POSITIVE LOGITS

 mere

0.46

Panamoan

0.46

 nameless

0.45

 Lightboxes

0.44

 simply

0.44

XMLSchema

0.43

mere

0.43

oporosis

0.42

 }}}{

0.42

Simply

0.41

Activations Density 0.094%

relationships between characters and their roles within narratives

just, simply, or merely

No Comments

No Known Activations