INDEX

Explanations

references to educational achievements and positions held

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ValueStyle

-0.66

دانشنامهٔ

-0.47

FunctionFlags

-0.45

XmlEnum

-0.44

ỡng

-0.44

 referrerpolicy

-0.43

 Wiktionnaire

-0.43

MemoryWarning

-0.41

Portály

-0.41

Personensuche

-0.40

POSITIVE LOGITS

ſelf

0.49

 verſ

0.47

 Anſ

0.47

Gul

0.47

SDP

0.46

 plufieurs

0.44

 ainfi

0.44

 deſt

0.44

 poffe

0.43

さえ

0.43

Activations Density 0.164%

references to educational achievements and positions held

No Comments

No Known Activations