INDEX

Explanations

structured elements or formatting in documentation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Portail

-0.79

NamedQueries

-0.65

NameInMap

-0.64

WriteTagHelper

-0.63

ChildScrollView

-0.60

endphp

-0.60

GOTREF

-0.58

 kasarigan

-0.57

etCode

-0.57

bolista

-0.57

POSITIVE LOGITS

 JADX

0.71

romycin

0.59

 levé

0.57

migrationBuilder

0.57

kháu

0.54

BufferException

0.50

 ItemStack

0.48

IsContent

0.48

ьаж

0.47

Revenir

0.47

Activations Density 0.148%

structured elements or formatting in documentation

No Comments

No Known Activations

structured elements or formatting in documentation

No Comments

No Known Activations