INDEX

Explanations

programming-related terms and structures within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

fromnode

-0.86

setVerticalGroup

-0.78

 HttpNotFound

-0.69

MessageTagHelper

-0.68

XmlAccessorType

-0.67

.*")]

-0.66

StoryboardSegue

-0.65

+:+

-0.64

AntiForgeryToken

-0.63

#+#

-0.61

POSITIVE LOGITS

 gyhoeddwyd

0.44

 partic

0.35

 gene

0.33

 regres

0.33

 poorly

0.31

 poden

0.31

krishnan

0.31

pun

0.30

ris

0.30

ceğine

0.29

Activations Density 0.854%

programming-related terms and structures within the document

No Comments

No Known Activations