INDEX

Explanations

terms related to electrical components 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 "..\..\

-0.93

__":

-0.89

__':

-0.88

 financières

-0.84

IsPostBack

-0.82

 Avery

-0.82

 bisous

-0.81

 doInBackground

-0.81

 Pitman

-0.80

 Weymouth

-0.80

POSITIVE LOGITS

App

0.85

App

0.79

Trả

0.70

 مشين

0.68

CoA

0.67

 Matsu

0.67

er

0.65

 aDecoder

0.63

 Appraisal

0.61

QApplication

0.60

Activations Density 0.088%

terms related to electrical components and systems

No Comments

No Known Activations