INDEX

Explanations

technical terms and jargon related to computer programming and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

oredCriteria

-0.72

 BoxFit

-0.62

 mergeFrom

-0.57

ніципа

-0.57

AddWithValue

-0.57

MessageOf

-0.56

ftagPool

-0.53

IndentedString

-0.52

 betweenstory

-0.52

 ویکی‌پدی

-0.50

POSITIVE LOGITS

出版年

0.70

varargin

0.67

 חיצוניים

0.60

 становника

0.58

[]:

0.57

__':

0.54

rony

0.54

 EconPapers

0.53

 varargin

0.51

 hanem

0.50

Activations Density 0.816%

technical terms and jargon related to computer programming and systems

No Comments

No Known Activations