INDEX

Explanations

references to procedural or technical terms and their implementations

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

WebVitals

-0.58

ClientSize

-0.50

XmlEnum

-0.47

Personendaten

-0.40

ArrowToggle

-0.38

kwij

-0.38

лами

-0.38

frente

-0.37

้ม

-0.36

 InputDecoration

-0.36

POSITIVE LOGITS

 second

3.13

second

2.81

Second

2.64

 Second

2.51

 SECOND

2.49

 secondly

2.37

SECOND

2.33

 seconde

2.23

第二

2.17

 segunda

2.15

Activations Density 0.558%

references to procedural or technical terms and their implementations

No Comments

No Known Activations