INDEX

Explanations

mathematical terminology and notation related to probability and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

<eos>

-0.61

<u>

-0.58

{@

-0.48

 then

-0.48

<b>

-0.47

<h1>

-0.46

ex

-0.45

-0.44

ex

-0.44

<strong>

-0.44

POSITIVE LOGITS

endphp

1.00

OGND

0.99

parsedMessage

0.98

ftagPool

0.92

 مشين

0.91

存于互联网档案馆

0.88

ględ

0.87

0.85

reportWebVitals

0.84

Personensuche

0.83

Activations Density 0.332%

mathematical terminology and notation related to probability and statistics

No Comments

No Known Activations