INDEX

Explanations

the beginning of a document or section

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

исленность

-0.55

apollo

-0.49

 bouche

-0.49

 goutte

-0.49

 addSubview

-0.48

 Stardust

-0.47

ecore

-0.47

didSet

-0.46

BindView

-0.46

vs

-0.45

POSITIVE LOGITS

 CreateTagHelper

1.18

 الحره

0.69

\{\\

0.63

Izvori

0.60

addPreferredGap

0.57

 Wikimedijinoj

0.56

ForValue

0.55

 الرياضيه

0.55

astéro

0.54

ItemBackground

0.54

Activations Density 0.060%

the beginning of a document or section

No Comments

No Known Activations