INDEX

Explanations

links and metadata related to articles or publications

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

原始内容存档于

-0.61

注釈

-0.60

 لينك

-0.52

SuccessListener

-0.52

GOTREF

-0.52

 NgModule

-0.51

PropertyChanging

-0.51

 Geraadpleegd

-0.50

ManagedBean

-0.49

 незавершена

-0.48

POSITIVE LOGITS

########.

0.73

 समीक्षाओं

0.71

IUrlHelper

0.63

Rhestr

0.61

SourceChecksum

0.59

RegistryLite

0.56

 snippetHide

0.56

 detonation

0.55

 Biôgrafia

0.54

oodoo

0.53

Activations Density 0.309%

links and metadata related to articles or publications

No Comments

No Known Activations