INDEX

Explanations

references to problems or tasks in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

mapStateToProps

-0.45

 PopupWindow

-0.43

AndView

-0.43

allowNull

-0.42

 viņ

-0.41

gdala

-0.40

वरण

-0.40

 bege

-0.39

эн

-0.39

 scoper

-0.39

POSITIVE LOGITS

出版年

0.98

Datuak

0.90

 betweenstory

0.83

 pleaſure

0.82

 متعلقه

0.77

 AssemblyTitle

0.76

 purpoſe

0.75

ercicio

0.74

 ſtate

0.74

 ***!

0.74

Activations Density 0.919%

references to problems or tasks in a structured format

No Comments

No Known Activations