INDEX

Explanations

coding terms and references related to Ruby specifications and testing frameworks

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

RSpec testing code

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-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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.75

aarrggbb

-0.52

UrlEncoded

-0.49

helmet

-0.47

copg

-0.47

出版年

-0.46

èdia

-0.44

angliski

-0.44

GraphicsUnit

-0.43

 beginnetje

-0.42

POSITIVE LOGITS

RSpec

4.56

rspec

1.55

 AssemblyTitle

0.67

TestBed

0.60

Spec

0.57

describe

0.57

spec

0.55

scalatest

0.53

 spec

0.52

setVerticalGroup

0.52

Activations Density 0.000%

coding terms and references related to Ruby specifications and testing frameworks

RSpec testing code

No Comments

No Known Activations