INDEX

Explanations

programming-related keywords and functionality

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

AndEndTag

-0.74

 NSError

-0.65

 informée

-0.63

Autoritní

-0.60

 незавершена

-0.59

OGND

-0.56

VideoCapture

-0.56

AutoField

-0.55

 Reverso

-0.55

Portale

-0.55

POSITIVE LOGITS

 decorativo

0.40

 llenar

0.38

 decoration

0.37

 Erscheinung

0.37

 decoraciones

0.37

 Stirn

0.36

PerformLayout

0.36

 penampilan

0.35

 göster

0.35

 decorations

0.34

Activations Density 0.175%

programming-related keywords and functionality

No Comments

No Known Activations