INDEX

Explanations

terminology related to mathematical proofs and formulations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

GTCX

-0.45

OGND

-0.44

bruik

-0.41

galkan

-0.40

 desg

-0.39

 käytt

-0.38

 diikuti

-0.38

 utafitiHapana

-0.38

ThroughAttribute

-0.37

wijl

-0.37

POSITIVE LOGITS

RectangleBorder

0.53

GEBURTSDATUM

0.50

zel

0.48

MessageTagHelper

0.46

MeasureSpec

0.46

 Waray

0.44

aarrggbb

0.44

Pun

0.44

 OnTrigger

0.43

 Biôgrafia

0.43

Activations Density 1.594%

terminology related to mathematical proofs and formulations

No Comments

No Known Activations