INDEX

Explanations

sections of text that involve categorization or formatting in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

JCheckBox

-0.56

وصلات

-0.48

 utafitiHapana

-0.47

+#+#

-0.47

 trebui

-0.46

 <<<<<<<<<<<<<<

-0.45

 hạt

-0.45

ppure

-0.44

 صوتيه

-0.43

de

-0.42

POSITIVE LOGITS

 Baillargeon

0.85

 defaultstate

0.82

ритори

0.75

存于互联网档案馆

0.70

ⓧ

0.70

styleType

0.68

 ThemeData

0.64

verwijspagina

0.64

UnsafeEnabled

0.64

↵↵↵↵↵↵↵↵

0.64

Activations Density 0.396%

sections of text that involve categorization or formatting in documents

No Comments

No Known Activations