INDEX

Explanations

references to time durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

veloppement

-0.39

 Weing

-0.39

 schlafen

-0.38

 ruote

-0.38

 iscri

-0.36

 armados

-0.36

 anzunehmen

-0.36

 çift

-0.35

 combatt

-0.35

 birlikte

-0.35

POSITIVE LOGITS

Minute

1.16

 Minute

1.15

 minute

1.14

getMinutes

1.13

 MINUTE

1.08

minute

1.07

 minuto

1.03

 minutes

1.03

minutes

1.01

Minutes

0.96

Activations Density 0.187%

references to time durations

No Comments

No Known Activations