INDEX

Explanations

references to programming concepts and terminology

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

programming keywords and constructs

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

 WebDriverWait

-0.33

 politischen

-0.32

 muchacha

-0.32

 dumne

-0.32

ambilan

-0.31

 Hinweise

-0.31

 internationalen

-0.31

นาน

-0.29

KommentareTeilen

-0.29

seguida

-0.29

POSITIVE LOGITS

 gynhyrchwyd

0.69

 CanadaChoose

0.64

XmlEnum

0.51

bobox

0.48

𝟹

0.47

XmlAccessType

0.47

rinfo

0.46

цездатний

0.46

bewerken

0.45

 linkovi

0.45

Activations Density 0.072%

references to programming concepts and terminology

programming keywords and constructs

No Comments

No Known Activations