INDEX

Explanations

mathematical expressions and notation related to statistical analysis or modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

iato

-0.53

 racc

-0.47

asInstanceOf

-0.46

ņš

-0.46

TargetException

-0.46

frac

-0.45

#+#

-0.44

siasi

-0.44

 coin

-0.44

PerformLayout

-0.44

POSITIVE LOGITS

SourceChecksum

0.83

 للاسماء

0.67

 propOrder

0.66

prefixer

0.66

contentLoaded

0.66

 Wikimedijinoj

0.64

 Мексичка

0.63

 дописавши

0.62

 gyhoeddwyd

0.61

NameInMap

0.60

Activations Density 0.795%

mathematical expressions and notation related to statistical analysis or modeling

No Comments

No Known Activations