INDEX

Explanations

mathematical structures and symbols used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.64

 فريبيس

-0.63

bootstrapcdn

-0.60

LLocation

-0.59

Kg

-0.58

 pegged

-0.58

esgue

-0.57

oneofs

-0.57

Ingestion

-0.57

EFF

-0.57

POSITIVE LOGITS

hdashline

1.14

\\

1.00

\\\

0.97

\\\

0.95

<tr>

0.89

hline

0.80

\\

0.76

}\\

0.73

 ***!

0.73

 purpoſe

0.72

Activations Density 0.188%

mathematical structures and symbols used in equations

No Comments

No Known Activations