INDEX

Explanations

proper nouns related to places, people, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 AssemblyCompany

-0.65

tagHelper

-0.59

 kaarangay

-0.56

 nahilalakip

-0.54

Gemeinden

-0.53

 rospy

-0.51

 intStringLen

-0.50

GEBURTSDATUM

-0.48

InteropServices

-0.48

 الرياضيه

-0.47

POSITIVE LOGITS

 ſever

0.82

 becauſe

0.75

 againſt

0.70

 raiſ

0.70

Efq

0.69

 Houſe

0.67

 houſe

0.67

 Cæsar

0.63

 Majefty

0.63

}],

0.62

Activations Density 0.562%

proper nouns related to places, people, and organizations

No Comments

No Known Activations