INDEX

Explanations

terms and concepts related to relevant studies, industry practices, and statutory provisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 NSCoder

-0.71

réhen

-0.59

ссора

-0.58

BeginInit

-0.56

 hanem

-0.55

 AssemblyCulture

-0.54

AddTagHelper

-0.53

ECAUSE

-0.52

pecker

-0.52

XmlAccessType

-0.51

POSITIVE LOGITS

Nearby

0.80

 nearby

0.72

nearby

0.70

 فريبيس

0.69

oneofs

0.63

 متعلقه

0.61

 Nearby

0.60

 المعيارى

0.60

 industry

0.57

 locally

0.57

Activations Density 0.397%

terms and concepts related to relevant studies, industry practices, and statutory provisions

No Comments

No Known Activations