INDEX

Explanations

comments and documentation 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SequentialGroup

-0.55

 CreateTagHelper

-0.54

ftagPool

-0.50

CodeAttribute

-0.50

verifyException

-0.49

DataAnnotations

-0.48

bootstrapcdn

-0.48

*/].

-0.47

<tfoot>

-0.47

 uLocal

-0.47

POSITIVE LOGITS

 Autorisations

0.48

SuspendLayout

0.43

 tässä

0.42

/*

0.40

Билгалдахарш

0.40

 vPvB

0.38

 hanem

0.38

webElementXpaths

0.37

 dipasang

0.37

 kwamba

0.36

Activations Density 0.062%

comments and documentation in code

No Comments

No Known Activations