INDEX

Explanations

mathematical symbols and notations relevant to equations

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

Ārējās

-0.46

::_('

-0.43

Erreferentziak

-0.42

 BoxFit

-0.40

AutoScale

-0.38

式

-0.38

gæ

-0.35

式

-0.35

protoimpl

-0.34

DataURL

-0.34

POSITIVE LOGITS

operatorname

0.50

ldots

0.49

Cyfarwyddwr

0.49

lcm

0.48

quad

0.47

|^{

0.47

bmod

0.47

 saveiro

0.47

|$

0.47

mid

0.47

Activations Density 0.500%

mathematical symbols and notations relevant to equations

No Comments

No Known Activations