INDEX

Explanations

technical terminology and patterns related to data processing 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 setuptools

-0.81

Geplaatst

-0.79

ChildScrollView

-0.75

apimachinery

-0.74

 doInBackground

-0.68

 NgModule

-0.67

NgModule

-0.67

AnchorStyles

-0.66

DeleteBehavior

-0.65

BindingResult

-0.64

POSITIVE LOGITS

 betweenstory

0.67

 spirit

0.56

spirit

0.55

 essence

0.54

inner

0.50

 Anth

0.50

Dij

0.50

 jadx

0.49

Mia

0.48

зен

0.47

Activations Density 0.503%

technical terminology and patterns related to data processing in code

No Comments

No Known Activations