INDEX

Explanations

parameters and attributes related to tensor shapes and operations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

PickerController

-0.77

 smtplib

-0.74

StoryboardSegue

-0.67



-0.64

󠁢

-0.64

-0.62

bootstrapcdn

-0.60

فایل‌لار

-0.58

MENAFN

-0.58

 JMenuItem

-0.58

POSITIVE LOGITS

shape

0.94

 shape

0.81

Shape

0.71

NameInMap

0.67

 Shape

0.65

 SHAPE

0.64

 size

0.63

SHAPE

0.62

DataType

0.55

rawQuery

0.55

Activations Density 0.051%

parameters and attributes related to tensor shapes and operations in programming contexts

No Comments

No Known Activations