INDEX

Explanations

details about authors, their works, and the themes within their stories

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

novel series authors

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

تقاوى

-0.58

цездатний

-0.56

 Numerade

-0.54

 CanadaChoose

-0.47

SequentialGroup

-0.46

 kasarigan

-0.44

Derbyniad

-0.43

withIdentifier

-0.41

tagHelperRunner

-0.40

featureID

-0.40

POSITIVE LOGITS

åga

0.43

 Schilder

0.43

ArrowToggle

0.40

BeginContext

0.40

PostInfinity

0.39

GenerationType

0.39

kale

0.39

 sauter

0.38

PYX

0.37

Activations Density 0.071%

details about authors, their works, and the themes within their stories

novel series authors

No Comments

No Known Activations