INDEX

Explanations

technical terms and numeric values related to programming and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Paglinawan

-0.97

Jeografia

-0.87

kháu

-0.85

 ویکی‌پدی

-0.85

WithIOException

-0.79

,:);

-0.78

:✨

-0.77

ουσ

-0.76

олові

-0.74

IsContent

-0.73

POSITIVE LOGITS

<strong>

0.65

<em>

0.63

<blockquote>

0.63

<h4>

0.62

<h5>

0.57

 urbanas

0.55

<h3>

0.53

<eos>

0.52

 encore

0.51

</td>

0.51

Activations Density 0.042%

technical terms and numeric values related to programming and data management

No Comments

No Known Activations