INDEX

Explanations

references to network ports in various contexts

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

networking port setup

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

脚注の使い方

-0.66

KommentareTeilen

-0.65

 GenerationType

-0.64

出版年

-0.59



-0.54

parsedMessage

-0.50

ChildScrollView

-0.50

MENAFN

-0.50

ſelf

-0.47

istible

-0.47

POSITIVE LOGITS

 port

0.59

 Port

0.57

Port

0.56

tonode

0.50

port

0.50

 PORT

0.46

 numbers

0.45

nummer

0.45

number

0.44

getPort

0.44

Activations Density 0.008%

references to network ports in various contexts

networking port setup

No Comments

No Known Activations