INDEX

Explanations

technical terms and data related to science and programming

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

 Reden

-0.38

gam

-0.37

epam

-0.34

ten

-0.33

iv

-0.32

chafter

-0.32

itaal

-0.32

net

-0.32

ci

-0.31

painter

-0.31

POSITIVE LOGITS

SourceChecksum

0.67

 AssemblyVersion

0.66

 arşivlendi

0.66

 AssemblyTitle

0.65

 виправивши

0.63

expandindo

0.62

AISSEE

0.60

HasForeignKey

0.57

IUrlHelper

0.56

dafx

0.56

Activations Density 0.423%

technical terms and data related to science and programming

No Comments

No Known Activations