INDEX

Explanations

technical terms and constructs related to network protocols and packet processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

getDoctrine

-0.35

 MainAxisSize

-0.30

 LCCN

-0.30

WritableDatabase

-0.29

 מר

-0.29

SharedDtor

-0.29

Acc

-0.28

rlrl

-0.28

Abit

-0.27

Acc

-0.27

POSITIVE LOGITS

PerformLayout

0.60

IsContent

0.59

 '\\;'

0.58

OGND

0.57

WebElementEntity

0.57

 فريبيس

0.56

verwijspagina

0.56

 transmissions

0.55

 unsolicited

0.55

 linkovi

0.54

Activations Density 0.459%

technical terms and constructs related to network protocols and packet processing

No Comments

No Known Activations