INDEX

Explanations

phrases related to analysis and categorization of various features or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

TagMode

-0.71

bootstrapcdn

-0.69

はじめに

-0.66

هرست

-0.64

ParallelGroup

-0.62

__*/

-0.62

afficheront

-0.61

EndInit

-0.60

>*/

-0.60

#+#

-0.59

POSITIVE LOGITS

 maybe

0.50

 autorytatywna

0.50

windowFixed

0.49

fortawesome

0.46

Legături

0.46

чало

0.45

ereich

0.45

endsection

0.44

ksa

0.44

geen

0.44

Activations Density 1.676%

phrases related to analysis and categorization of various features or components

No Comments

No Known Activations