INDEX

Explanations

terms related to programming and software development

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

gtk tree view iteration

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

makeText

-0.63

ViewImports

-0.53

HasForeignKey

-0.45

PMailer

-0.43

assertj

-0.43

 مشين

-0.37

ConstraintMaker

-0.36

 indietro

-0.36

databind

-0.36

ostante

-0.36

POSITIVE LOGITS

 ProtoMessage

0.79

protoimpl

0.71

BagLayout

0.66

 TType

0.55

 ویکی‌پدی

0.54

Princip

0.51

LookAnd

0.50

 Princip

0.50

يكب

0.49

HomeAsUpEnabled

0.49

Activations Density 0.019%

terms related to programming and software development

gtk tree view iteration

No Comments

No Known Activations