INDEX

Explanations

elements related to programming concepts, particularly those pertaining to variable declarations and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 hende

-0.59

ffekt

-0.45

ennia

-0.43

šinou

-0.42

Diweddarwch

-0.40

besch

-0.39

 trai

-0.39

 дописавши

-0.39

 intérêt

-0.39

preuves

-0.39

POSITIVE LOGITS

SharedDtor

0.75

 GenerationType

0.65

titleMargin

0.64

MetaObject

0.64

kháu

0.64

Filmographie

0.61

bootstrapcdn

0.60

Przypisy

0.60

-------

0.59

 adipis

0.59

Activations Density 1.030%

elements related to programming concepts, particularly those pertaining to variable declarations and their attributes

No Comments

No Known Activations