INDEX

Explanations

terms related to programming and legal jargon, particularly in the context of software documentation and court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 profesional

-0.56

üyada

-0.56

HasForeignKey

-0.55

Poppins

-0.54

[]=$

-0.53

 unknownFields

-0.53

Історія

-0.53

⟶

-0.52

ÁS

-0.51

Открыть

-0.50

POSITIVE LOGITS

存于互联网档案馆

0.99

 متعلقه

0.97

enumi

0.91

\{\\

0.72

WarningLevel

0.71

jspx

0.71

 EconPapers

0.70

 typelib

0.66

\}\\

0.65

enumii

0.64

Activations Density 0.001%

terms related to programming and legal jargon, particularly in the context of software documentation and court proceedings

No Comments

No Known Activations