INDEX

Explanations

prepositions indicating relationships or connections within text

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

 Normdatei

-0.84

 CreateTagHelper

-0.80

providedIn

-0.75

 للاسماء

-0.73

 للمعارف

-0.73

 ostavi

-0.73

protoimpl

-0.71

ichord

-0.70

//

-0.68

arakhand

-0.68

POSITIVE LOGITS

 miles

0.78

 kilomètres

0.67

km

0.67

 mile

0.67

miles

0.65

km

0.65

scrapy

0.63

 long

0.63

mile

0.62

 dài

0.62

Activations Density 0.001%

prepositions indicating relationships or connections within text

No Comments

No Known Activations