INDEX

Explanations

programming-related syntax and constructs

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

require

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

:✨

-0.84

BufferException

-0.65

 protoimpl

-0.59

posedge

-0.57

prepareStatement

-0.57

出版年

-0.56

SharedCtor

-0.54

momix

-0.53

__':

-0.52

 OFDb

-0.52

POSITIVE LOGITS

Independent

0.37

 autorytatywna

0.35

Ghana

0.34

 Kais

0.33

 vicente

0.30

 Independent

0.30

 edildi

0.29

Explicit

0.29

 Drapeau

0.29

ensor

0.28

Activations Density 0.011%

programming-related syntax and constructs

require

No Comments

No Known Activations