INDEX

Explanations

elements or annotations related to documentation in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 ſta

-0.49

ſelves

-0.45

ſelf

-0.45

 quæ

-0.44

 ſtre

-0.43

 houſe

-0.42

 albic

-0.42

 weak

-0.39

 Weak

-0.39

Wow

-0.39

POSITIVE LOGITS

GEBURTSDATUM

0.70

Viitteet

0.58

Javadoc

0.48

ollectionView

0.48

SequentialGroup

0.45

 AssemblyCulture

0.43

IContainer

0.43

TestingModule

0.42

 Référence

0.42

Descripción

0.41

Activations Density 0.045%

elements or annotations related to documentation in code

No Comments

No Known Activations