INDEX

Explanations

recommendations for products and services

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

Positive sentiment for locations or options

np_acts-logits-general · gemini-2.0-flash

ideal suitability or choice

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ViewFeatures

-0.71

MessageOf

-0.68

jspx

-0.62

IUrlHelper

-0.62

TableBody

-0.60

 ModelExpression

-0.59

 صوتيه

-0.57

Література

-0.57

bootstrapcdn

-0.57

 تضيفلها

-0.56

POSITIVE LOGITS

 geeignet

0.67

 hvis

0.63

 banget

0.63

for

0.54

 jeśli

0.54

if

0.54

 Eğer

0.53

nextDouble

0.53

 beginners

0.52

 when

0.52

Activations Density 0.170%

recommendations for products and services

Positive sentiment for locations or options

ideal suitability or choice

No Comments

No Known Activations