INDEX

Explanations

comments and code relating to error handling and processing logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ViewImports

-0.53

 виправивши

-0.51

 sinned

-0.51

hamshire

-0.50

offsetof

-0.49

ButtonStyle

-0.47

แท

-0.47

 chi̍t

-0.46

parency

-0.45

UserController

-0.45

POSITIVE LOGITS

WillAppear

0.72

 noDo

0.64

TODO

0.62

 TODO

0.60

 дописавши

0.59

脚注の使い方

0.58

 الحره

0.58

XmlAccessType

0.57

 Lightboxes

0.56

 NotImplemented

0.56

Activations Density 0.233%

comments and code relating to error handling and processing logic

No Comments

No Known Activations