INDEX

Explanations

HTML structure elements and tags

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

xml tags and user input

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

 otomatig

-0.83

########.

-0.79

 utafitiHapana

-0.76

 queſta

-0.72

WebServlet

-0.71

MigrationBuilder

-0.71

 שוליים

-0.70

 müſſen

-0.67

OGND

-0.67

expandindo

-0.66

POSITIVE LOGITS

CardHeader

0.30

Modern

0.29

 вывод

0.28

Reading

0.28

 خارجية

0.26

Base

0.26

 pré

0.25

 presente

0.25

 Reading

0.24

Top

0.24

Activations Density 0.004%

HTML structure elements and tags

xml tags and user input

No Comments

No Known Activations