INDEX

Explanations

phrases related to residency and living situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.71

 pleaſure

-0.63

الحياه

-0.61

CloseOperation

-0.60

tableFuture

-0.60

 Monfieur

-0.57

 ſta

-0.57

IBOutlet

-0.57

DataAnnotations

-0.56

 leaſt

-0.56

POSITIVE LOGITS

 lived

0.44

 Lived

0.44

 Spuren

0.39

lived

0.37

 resided

0.37

 thrived

0.35

 lebte

0.33

 Flucht

0.32

 ErrIntOverflow

0.32

 мәкал

0.32

Activations Density 0.000%

phrases related to residency and living situations

No Comments

No Known Activations