INDEX

Explanations

mathematical terminology and symbols related to linear algebra and topology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <<<<<<<<<<<<<<

-0.70

<eos>

-0.66

<u>

-0.55

 such

-0.52

 moment

-0.50

<b>

-0.48

<strong>

-0.47

enthe

-0.47

-0.43

van

-0.43

POSITIVE LOGITS

-}

0.91

 مشين

0.90

 myſelf

0.87

ględ

0.83

OGND

0.80

 Jefus

0.79

ftagPool

0.79

Efq

0.79

,}

0.78

 himſelf

0.78

Activations Density 0.204%

mathematical terminology and symbols related to linear algebra and topology

No Comments

No Known Activations