INDEX

Explanations

references to specific rows in data structures or databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

NewUrlParser

-0.78

 صوتيه

-0.62

ContentLoaded

-0.61

 getRule

-0.59

 ivelany

-0.56

 bezeichneter

-0.56

Datuak

-0.56

bilirsiniz

-0.56

Mutagenicity

-0.55

Réponse

-0.55

POSITIVE LOGITS

Row

2.36

Row

1.79

ROW

0.97

 Rowe

0.88

ROW

0.86

Column

0.77

 Rowland

0.77

ForRow

0.72

 Rowley

0.69

Raw

0.67

Activations Density 0.061%

references to specific rows in data structures or databases

No Comments

No Known Activations