INDEX

Explanations

references to programming components and structures 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-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



-1.01

parsedMessage

-0.93

 مشين

-0.88

BeginContext

-0.82

ValueStyle

-0.80

 Taktlose

-0.80

-------------</

-0.79

PerformLayout

-0.79

EndInit

-0.78

 ſta

-0.77

POSITIVE LOGITS

 işte

0.33

my

0.29

his

0.27

 your

0.26

 settled

0.26

 않는

0.25

 ifade

0.25

 harap

0.25

 sienta

0.24

ríamos

0.24

Activations Density 0.037%

references to programming components and structures in code

No Comments

No Known Activations