INDEX

Explanations

programming-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 myſelf

-0.63

 يتيمه

-0.59

 didst

-0.58

蚪

-0.57

 Verſ

-0.54

ArrowToggle

-0.54

 Taktlose

-0.53

ModelSerializer

-0.51

aspectj

-0.51

Życiorys

-0.51

POSITIVE LOGITS

return

0.50

providedIn

0.49

findOrFail

0.47

 getItemCount

0.46

Abitanti

0.41

RTCK

0.41

.”

0.41

endif

0.39

</tr>

0.38

Activations Density 0.119%

programming-related syntax and structures

No Comments

No Known Activations