INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 autorytatywna

-0.63

bootstrapcdn

-0.62

VIAF

-0.59

GOTREF

-0.57

 dAtA

-0.56

esModule

-0.55

TagMode

-0.54

parsedMessage

-0.54

 CURLOPT

-0.54

elemField

-0.54

POSITIVE LOGITS

2.14

1.59

ｘ

1.02

х

1.02

0.99

𝑥

0.77

xx

0.72

х

0.69

خ

0.68

Activations Density 1.546%

mathematical expressions and symbols

No Comments

No Known Activations