INDEX

Explanations

keywords and constructs related to programming and declarations 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 @ 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

ReusableCell

-0.64

ğim

-0.63

chließend

-0.63

ostante

-0.60

ğiniz

-0.59

ğimiz

-0.57

 lenker

-0.55

rillos

-0.54

InputTagHelper

-0.54

 متعلقه

-0.54

POSITIVE LOGITS

 betweenstory

0.62

 predeceased

0.57

 intStringLen

0.56

DataSetChanged

0.54

cplusplus

0.50

 contextLoads

0.49

AnimationsModule

0.48

 albedo

0.46

Personensuche

0.46

randomUUID

0.45

Activations Density 0.047%

keywords and constructs related to programming and declarations in code

No Comments

No Known Activations