INDEX

Explanations

occurrences of the term "init" and its variations related to initialization in programming contexts

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

 McCar

-0.83

jsxFileName

-0.71

ToMany

-0.70

 springfox

-0.69

ETRIC

-0.66

mektedir

-0.63

 Stro

-0.63

aronder

-0.62

mern

-0.62

qvarna

-0.61

POSITIVE LOGITS

init

1.86

 init

1.82

INIT

1.78

 INIT

1.69

Init

1.66

 Init

1.66

 initState

1.31

 initialization

1.25

 初始化

1.22

 Initializes

1.18

Activations Density 0.048%

occurrences of the term "init" and its variations related to initialization in programming contexts

No Comments

No Known Activations