INDEX

Explanations

numerical representations or references to posts and responses in a digital context

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

INSEE

-0.63

 المعيارى

-0.60

stateProvider

-0.56

IndentedString

-0.56

bitField

-0.54

⟬

-0.54

SharedDtor

-0.53

queryInterface

-0.53

ьаж

-0.52

 Infórmanos

-0.52

POSITIVE LOGITS

RegressionTest

0.56

expandindo

0.52

ISupport

0.42

BeginContext

0.41

principalTable

0.39

 autorytatywna

0.36

MessageOf

0.36

 tartalomajánló

0.34

/***/

0.33

 CreateTagHelper

0.33

Activations Density 0.187%

numerical representations or references to posts and responses in a digital context

No Comments

No Known Activations