INDEX

Explanations

code elements related to software project dependencies and configurations

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

XML or JSON properties and tags

np_acts-logits-general · gemini-2.0-flash

structured data keys and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MessageOf

-0.63

 estekak

-0.60

MessageTagHelper

-0.55

ⓧ

-0.51

WriteLiteral

-0.50

 kenyataan

-0.50

#+#

-0.50

 <<<<<<<<<<<<<<

-0.47

 nadzieję

-0.47

mbggenerated

-0.46

POSITIVE LOGITS

 AssemblyTitle

0.85

 createSprite

0.54

 AssemblyProduct

0.49

 CreateTagHelper

0.49

beginPath

0.44

ThroughAttribute

0.44

qtype

0.40

SerializedName

0.40

ngdoc

0.39

 nahilalakip

0.39

Activations Density 0.487%

code elements related to software project dependencies and configurations

XML or JSON properties and tags

structured data keys and values

No Comments

No Known Activations