INDEX

Explanations

indicators of a significant shift in context or topics throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 newOwner

-0.65

LookAnd

-0.63

@"/

-0.62

 betweenstory

-0.59

queryInterface

-0.51

UnsafeEnabled

-0.51

 accounts

-0.51

IUrlHelper

-0.49

 typelib

-0.49

 Drapeau

-0.48

POSITIVE LOGITS

itinéraire

0.71

 HasFactory

0.71

новништво

0.70

NullCheck

0.60

 AspNetCore

0.59

 condenado

0.58

 CYTHON

0.58

pieza

0.58

 useAppContext

0.58

autique

0.57

Activations Density 0.271%

indicators of a significant shift in context or topics throughout the document

No Comments

No Known Activations