INDEX

Explanations

programming language elements and warnings related to memory management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

createTextNode

-0.56

ขึ้น

-0.53

น้อย

-0.52

Кры

-0.52

Tar

-0.51

sifs

-0.50

'">

-0.49

rawDesc

-0.49

جب

-0.48

ElementException

-0.48

POSITIVE LOGITS

ISupport

4.71

EndInit

1.66

ResumeLayout

1.53

BeginInit

1.30

UseVisualStyle

1.04

GEBURTSDATUM

0.90

 AssemblyTitle

0.87

PerformLayout

0.85

SuspendLayout

0.84

تقاوى

0.79

Activations Density 0.006%

programming language elements and warnings related to memory management

No Comments

No Known Activations