INDEX

Explanations

references to evidence and support within legal contexts

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

CloseOperation

-0.59

 ProtoMessage

-0.58

TypedDataSet

-0.51



-0.49

nonatomic

-0.48

.*")]

-0.48

بوابة

-0.46

ToRefresh

-0.46

 EconPapers

-0.45

 CreateTagHelper

-0.45

POSITIVE LOGITS

GOTREF

0.60

 mukaan

0.38

 layak

0.37

 kysy

0.37

eseorang

0.37

 mérit

0.37

deserved

0.36

 lemn

0.36

 prétend

0.35

 Umum

0.35

Activations Density 0.146%

references to evidence and support within legal contexts

No Comments

No Known Activations