INDEX

Explanations

numerical identifiers or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Hentet

-0.55

 للمعارف

-0.54

 propOrder

-0.53

 betreft

-0.52

 například

-0.50

 zboží

-0.50

 varandra

-0.50

makeConstraints

-0.50

Aktualisiert

-0.49

CloseOperation

-0.47

POSITIVE LOGITS

 المعيارى

0.47

Wra

0.42

 cref

0.41

CppCodeGen

0.41

law

0.41

 rescue

0.40

copyOf

0.40

 OnEnable

0.40

BASEPATH

0.40

 macOS

0.40

Activations Density 0.195%

numerical identifiers or references

No Comments

No Known Activations