INDEX

Explanations

code blocks and programming constructs in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

再见

-0.41

 pacto

-0.41

حياته

-0.39

य

-0.38

 procu

-0.38

entran

-0.38

ことができました

-0.38

mer

-0.37

 hội

-0.35

 이용

-0.35

POSITIVE LOGITS

expandindo

0.86

:✨

0.81

ftagPool

0.79

DeleteBehavior

0.78

 estekak

0.78

 &___

0.78

ंदीखरीदारी

0.77

parsedMessage

0.75

########.

0.74

 للمعارف

0.74

Activations Density 0.317%

code blocks and programming constructs in the document

No Comments

No Known Activations