INDEX

Explanations

punctuations related to dialogue or quotations

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

":

-1.33

"…

-1.30

”:

-1.28

)”.

-1.26

"،

-1.26

".

-1.26

.,"

-1.26

-1.25

”…

-1.24

”).

-1.24

POSITIVE LOGITS

0.55

 there

0.53

uidado

0.53

no

0.52

and

0.52

Her

0.51

 around

0.50

 with

0.48

 culturelles

0.48

 here

0.48

Activations Density 0.129%

punctuations related to dialogue or quotations

No Comments

No Known Activations