INDEX

Explanations

repeated phrases or concepts throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Aiheesta

-0.71

PreferredItem

-0.67

tvguidetime

-0.66

وردار

-0.66

 ExecuteAsync

-0.63

endregion

-0.63

 nonché

-0.62

Portail

-0.60

argout

-0.60

 EdgeInsets

-0.59

POSITIVE LOGITS

1.41

1.27

And

1.20

\&

1.15

And

1.14

\&

1.08

and

1.05

&-

1.03

＆

0.99

AND

0.98

Activations Density 0.621%

repeated phrases or concepts throughout the text

No Comments

No Known Activations