INDEX

Explanations

references to document rows and their counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Réponses

-0.73

MENAFN

-0.72

QMetaType

-0.70

 sanitarios

-0.69

 termica

-0.67

 Escolar

-0.66

رير

-0.66

 sneezing

-0.64

istos

-0.64

astéroïdes

-0.63

POSITIVE LOGITS

row

1.08

 rows

1.05

Row

1.05

 numberOfRows

0.95

 Rowland

0.93

ROW

0.92

TypedDataSet

0.90

 Rows

0.84

Row

0.83

row

0.82

Activations Density 0.087%

references to document rows and their counts

No Comments

No Known Activations