INDEX

Explanations

elements related to legal proceedings and implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BASEPATH

-0.79

TableAdapter

-0.70

<bos>

-0.68

IBAction

-0.64

 TestBed

-0.63

DebuggerNonUser

-0.63

MLLoader

-0.61

шаем

-0.61

UMBIA

-0.60

ArgumentParser

-0.59

POSITIVE LOGITS

//$

0.47

 pinulongan

0.46

 مرئيه

0.41

 Morgen

0.40

/-

0.38

 AssemblyProduct

0.38

RESUMO

0.38

 Rings

0.38

 ВА

0.37

écriture

0.37

Activations Density 1.321%

elements related to legal proceedings and implications

No Comments

No Known Activations