INDEX

Explanations

structured data and metadata representation in documents

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

statistics, tables, code

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

 FBref

-0.46

atguigu

-0.44

openzeppelin

-0.43

convite

-0.43

躇

-0.41

ComponentModel

-0.41

ambién

-0.40

 noël

-0.40

 Fútbol

-0.40

drawSprites

-0.40

POSITIVE LOGITS

Personendaten

0.77

 '\\;'

0.68

Personensuche

0.60

bitField

0.48

хьтан

0.47

|}

0.44

staticmethod

0.44

يميديا

0.43

 &___

0.43

NameInMap

0.43

Activations Density 0.002%

structured data and metadata representation in documents

statistics, tables, code

No Comments

No Known Activations