INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

EDEFAULT

-0.64

featureID

-0.62

AccessorTable

-0.57

 jScrollPane

-0.56

FieldBuilder

-0.53

SharedCtor

-0.53

 CGRect

-0.48

CppMethod

-0.48

PDI

-0.47

contentLoaded

-0.47

POSITIVE LOGITS

xase

0.52

 Schmuck

0.49

agama

0.46

nuevos

0.46

 almend

0.45

 appréci

0.45

 almendras

0.45

 české

0.45

 henkilö

0.44

holdet

0.44

Activations Density 1.343%

mathematical symbols and notations

No Comments

No Known Activations