INDEX

Explanations

symbols and notation used in mathematical or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 Autorisations

-0.61

ArrowToggle

-0.46

 defaultstate

-0.44

RegressionTest

-0.42

WriteTagHelper

-0.42

ftagPool

-0.40

verwijspagina

-0.39

endpush

-0.38

mdash

-0.37

simpleType

-0.37

POSITIVE LOGITS

mathrm

0.80

AA

0.52

pm

0.48

舺

0.47

 Infór

0.45

Datuak

0.44

{~

0.43

 panoramique

0.41

 Numerade

0.41

 crochê

0.41

Activations Density 0.039%

symbols and notation used in mathematical or scientific context

No Comments

No Known Activations