INDEX

Explanations

complex scientific or mathematical terminology and notation

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

math notation and programming symbols

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

 Lingkungan

-0.49

Aholisi

-0.46

 nahilalakip

-0.42

bootstrapcdn

-0.40

lindungan

-0.40

 Signalez

-0.39

getMenuInflater

-0.39

WriteTagHelper

-0.39

flashdata

-0.38

Compartir

-0.38

POSITIVE LOGITS

 ujednoznacz

0.45

 تعدى

0.42

contentLoaded

0.40

魔王

0.39

weer

0.39

agami

0.37

EndProject

0.37

 agencias

0.36

SpringRunner

0.35

 Troll

0.35

Activations Density 0.645%

complex scientific or mathematical terminology and notation

math notation and programming symbols

No Comments

No Known Activations