INDEX

Explanations

return statements, particularly related to data structures and conditions

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

prefixer

-0.49

randomUUID

-0.48

__":

-0.47

}]{

-0.47

diğini

-0.45

Instead

-0.45

antaine

-0.45

\|_{

-0.44

__':

-0.44

ReusableCell

-0.44

POSITIVE LOGITS

((

2.02

((

1.99

>((

1.69

[(

1.62

[(

1.57

(((

1.53

)((

1.48

(((

1.38

=((

1.28

(($

1.27

Activations Density 0.373%

return statements, particularly related to data structures and conditions

No Comments

No Known Activations