INDEX

Explanations

technical terms and jargon related to programming and software development

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

complexContent

-0.46

 testator

-0.46

новништво

-0.46

tonode

-0.45

ModelBuilder

-0.44

ſchaft

-0.44

alista

-0.43

coil

-0.43

 bowiem

-0.43

 Longevity

-0.43

POSITIVE LOGITS

 kasarigan

0.58

InitVars

0.48

Παραπομπές

0.44

 externi

0.43

 فريبيس

0.43

الحياه

0.42

 Exacts

0.41

ErrUnexpectedEOF

0.40



0.39

 تضيفلها

0.38

Activations Density 0.090%

technical terms and jargon related to programming and software development

No Comments

No Known Activations