INDEX

Explanations

phrases that indicate a temporal or contextual setting, particularly prepositions and introductory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

principalTable

-1.30

KommentareTeilen

-1.13

 disambiguazione

-1.07

 Roskov

-1.05

Personensuche

-1.01

MigrationBuilder

-1.00

 continúas

-0.97

 pinulongan

-0.95

المناصب

-0.91

*/;

-0.91

POSITIVE LOGITS

In

1.21

In

1.16

At

0.95

At

0.92

As

0.90

As

0.86

By

0.84

For

0.80

By

0.77

To

0.76

Activations Density 0.398%

phrases that indicate a temporal or contextual setting, particularly prepositions and introductory phrases

No Comments

No Known Activations