INDEX

Explanations

programming constructs related to class or function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

OGND

-0.76

 незавершена

-0.70

oa̍t

-0.61

 Wiktionnaire

-0.56

تقاوى

-0.55

 وتسجيلات

-0.55

rungsseite

-0.53

VYMaps

-0.53

الحياه

-0.52

 يتيمه

-0.51

POSITIVE LOGITS

func

0.93

 func

0.91

lazy

0.54

 convenience

0.54

convenience

0.51

var

0.50

var

0.48

struct

0.48

 internal

0.47

 struct

0.46

Activations Density 0.318%

programming constructs related to class or function definitions

No Comments

No Known Activations