INDEX

Explanations

mentions of attributes in programming contexts, particularly related to HTML or XML

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 initComponents

-0.68

 XCTest

-0.53

 Wicidata

-0.52

 bitter

-0.50

добно

-0.49

gesteld

-0.49

ButtonPressed

-0.49

naeus

-0.48

antd

-0.48

POSITIVE LOGITS

 attribute

1.44

 ATTR

1.33

 Attribute

1.31

 attr

1.29

 appeal

1.28

 Attributes

1.24

Att

1.24

attr

1.21

 Attr

1.20

 attraction

1.17

Activations Density 0.104%

mentions of attributes in programming contexts, particularly related to HTML or XML

No Comments

No Known Activations