INDEX

Explanations

references to studies, surveys, or reports related to scientific measurements or inventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

expandindo

-0.75

 Мексичка

-0.69

Vidite

-0.67

CodedInputStream

-0.66

<()>

-0.62

twimg

-0.62

archiviato

-0.61

principalColumn

-0.60

verwijspagina

-0.59

зулта

-0.59

POSITIVE LOGITS

 zufolge

0.60

 متعلقه

0.54

 mukaan

0.51

 göre

0.47

Según

0.46

 said

0.46

 अनुसार

0.45

scheduled

0.45

Согласно

0.45

leneck

0.43

Activations Density 0.286%

references to studies, surveys, or reports related to scientific measurements or inventions

No Comments

No Known Activations