INDEX

Explanations

mathematical symbols and structures, particularly within equations and formal definitions

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

mathematical notation and code variables

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

AndroidJUnit

-0.68

 MainAxisSize

-0.66

OGND

-0.54

ături

-0.54

AsUp

-0.52

Hentet

-0.51

 незавершена

-0.50

tonsoft

-0.50

mappedBy

-0.49

abetes

-0.49

POSITIVE LOGITS

WillAppear

0.38

afficheront

0.37

 Reusable

0.34

findpost

0.33

Hamburg

0.33

Raw

0.33

 spir

0.32

Garbage

0.31

 vira

0.31

Load

0.31

Activations Density 0.058%

mathematical symbols and structures, particularly within equations and formal definitions

mathematical notation and code variables

No Comments

No Known Activations