INDEX

Explanations

references to academic papers and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antMatchers

-0.55

Pvt

-0.51

Pvt

-0.50

ảy

-0.49

imageshack

-0.49

 Saxe

-0.49

kháu

-0.48

scheid

-0.47

onBackPressed

-0.47

OwnProperty

-0.47

POSITIVE LOGITS

ंदीखरीदारी

0.91

 nahilalakip

0.81

AndroidJUnit

0.71

TestingModule

0.70

 مرئيه

0.67

RenderAtEndOf

0.67

 estekak

0.66

 endregion

0.65

<i>

0.64

AddTagHelper

0.62

Activations Density 0.042%

references to academic papers and proceedings

No Comments

No Known Activations