INDEX

Explanations

phrases indicating quantitative analysis or measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

enumi

-0.48

致

-0.44

lap

-0.42

 pytest

-0.40

Afficher

-0.39

IGraphics

-0.38

 CreateTagHelper

-0.38

APIView

-0.38

TableBody

-0.37

 AdapterView

-0.37

POSITIVE LOGITS

 AssemblyVersion

0.77

UnknownFields

0.74

pédie

0.72

arschu

0.72

="@+

0.68

ьаж

0.68

balleur

0.67

ništvo

0.67

ГЛА

0.67

uterte

0.67

Activations Density 0.363%

phrases indicating quantitative analysis or measurement

No Comments

No Known Activations