INDEX

Explanations

specific formatting or structure in written content

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

 esternos

-0.58

+#+

-0.50

 nakalista

-0.50

 المعيارى

-0.49

 оригіналу

-0.49

 فريبيس

-0.48

原始内容存档于

-0.46

Referanser

-0.45

Trayectoria

-0.45

 GRANT

-0.43

POSITIVE LOGITS

webElementXpaths

0.57

/**

0.54

 Италијани

0.47

цездатний

0.46

ArrowToggle

0.45

 resourceCulture

0.41

jsii

0.38

">{{$

0.38

orghini

0.36

皆

0.36

Activations Density 0.200%

specific formatting or structure in written content

No Comments

No Known Activations