INDEX

Explanations

occurrences of the abbreviation "Ed" related to legal or educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 aikana

-0.71

 بيها

-0.70

ötzlich

-0.68

͗

-0.64

adering

-0.63

 viewType

-0.61

ナメント

-0.61

nhung

-0.59

columnHeader

-0.59

präche

-0.59

POSITIVE LOGITS

</td>

1.06

Portail

0.78

 jsPsych

0.65

subsection

0.63

</th>

0.58

subsubsection

0.57

Hozzáférés

0.57

testcase

0.56

']){

0.56

invokeLater

0.55

Activations Density 0.035%

occurrences of the abbreviation "Ed" related to legal or educational contexts

No Comments

No Known Activations