INDEX

Explanations

references to specific websites or applications, along with their promotional details or functionalities

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

tech company names

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

 actionTypes

-0.47

}{*}{

-0.41

<?

-0.37

 InputDecoration

-0.35

 propOrder

-0.35

InputBorder

-0.35

ประกอบ

-0.34

ContentAlignment

-0.34

 usual

-0.33

 DbType

-0.33

POSITIVE LOGITS

 platform

0.73

CEO

0.68

 Platform

0.66

pulseira

0.66

 SaaS

0.65

 Labs

0.63

platform

0.62

 analytics

0.61

 Technologies

0.60

 Analytics

0.59

Activations Density 0.040%

references to specific websites or applications, along with their promotional details or functionalities

tech company names

No Comments

No Known Activations