INDEX

Explanations

references to contrasts or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Paglinawan

-0.62

 referenties

-0.59

ContentAsync

-0.55

'}';

-0.54

ValueStyle

-0.51

paravant

-0.51

setCenter

-0.50

 AppBundle

-0.50

StateToProps

-0.49

centes

-0.49

POSITIVE LOGITS

 extreme

0.86

extreme

0.81

 autorytatywna

0.73

 hand

0.70

end

0.69

 extre

0.66

Extreme

0.66

adpleegd

0.65

expandindo

0.58

 ekst

0.58

Activations Density 0.127%

references to contrasts or comparisons

No Comments

No Known Activations