INDEX

Explanations

programming terminology and structure in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SqlClient

-0.53

aja

-0.43

 explo

-0.43

InputType

-0.43

أن

-0.42

cium

-0.42

ORIAL

-0.42

ято

-0.41

 envol

-0.41

 contrase

-0.41

POSITIVE LOGITS

 NSCoder

1.07

 onCreateView

1.04

onViewCreated

0.93

MemoryWarning

0.92

RenderAtEndOf

0.90

ngOnInit

0.87

ReusableCell

0.87

viewDidLoad

0.84

 Normdatei

0.83

posedge

0.80

Activations Density 0.232%

programming terminology and structure in code

No Comments

No Known Activations