INDEX

Explanations

phrases related to declarations and conflicting interests

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

references to interactions and relationships between people

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

joining phrases, abbreviations, or numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 fiable

-0.50

 graines

-0.45

 بتوان

-0.44

못

-0.43

榜

-0.43

 Mortuary

-0.42

 mente

-0.42

 запас

-0.41

rê

-0.41

 παρά

-0.41

POSITIVE LOGITS

verwijspagina

1.04

tagHelperRunner

1.00

 kaarangay

0.86

awtextra

0.86

IUrlHelper

0.85

DockStyle

0.85

 autorytatywna

0.80

 defaultstate

0.79

 CreateTagHelper

0.78

dafx

0.77

Activations Density 0.006%

phrases related to declarations and conflicting interests

references to interactions and relationships between people

joining phrases, abbreviations, or numbers

No Comments

No Known Activations