INDEX

Explanations

references to programming functions and data structures, particularly in the context of complex or mathematical operations

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

Apache commons math library and tests

np_acts-logits-general · gemini-2.0-flash

apache commons math tests

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

zule

-0.44

seiti

-0.43

fritt

-0.41

Leggi

-0.40

 abstrato

-0.39

ことはない

-0.38

<strong>

-0.37

ilor

-0.36

zIndex

-0.36

Txn

-0.36

POSITIVE LOGITS

DockStyle

0.84

IntoConstraints

0.70

bootstrapcdn

0.68

 propOrder

0.63

CloseOperation

0.63

HtmlAttribute

0.63

titleMargin

0.59

SourceChecksum

0.59

WebServlet

0.58

 ProtoMessage

0.57

Activations Density 0.306%

references to programming functions and data structures, particularly in the context of complex or mathematical operations

Apache commons math library and tests

apache commons math tests

No Comments

No Known Activations