INDEX

Explanations

coding patterns related to memory allocation and logging functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

prüche

-0.93

 tartalomajánló

-0.82

Demografía

-0.82

featureID

-0.80

 ExecuteAsync

-0.79

 تكبرها

-0.79

setVerticalGroup

-0.79

 ostavi

-0.77

NOPQRST

-0.76

phazard

-0.75

POSITIVE LOGITS

 EdgeInsets

2.71

EdgeInsets

0.81

gdx

0.70

 InputDecoration

0.68

ConstraintMaker

0.61

wpi

0.57

 cref

0.51

__(

0.50

 BorderRadius

0.49

DotNetBar

0.48

Activations Density 0.022%

coding patterns related to memory allocation and logging functions

No Comments

No Known Activations